CVE-2026-82579 (GCVE-0-2026-82579)
Vulnerability from cvelistv5 – Published: 2026-08-31 01:07 – Updated: 2026-08-31 16:05
VLAI
EPSS
VEX
Title
AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service
Summary
Loop with Unreachable Exit Condition (Infinite Loop) vulnerability in ash-project ash_ai allows an attacker who can influence a model's output to hang the tool loop and drive unbounded, repeated model requests.
AshAi.ToolLoop classifies a model response of :tool_calls, then filters the calls through normalize_tool_calls/2 and unprocessed_tool_calls/2. Both can empty the list: a call missing a valid name, or one reusing a tool_call_id that already has a result in history, is dropped. With an empty list the loop appended nothing and recursed with a byte-identical message list, so the conversation never advanced and the same request was re-sent every iteration. Under the supported max_iterations: :infinity this never terminated; otherwise it exhausted the full budget. Prompt-injected content can make the model re-emit a spent tool_call_id. The fix treats an empty post-filter list as terminal.
This issue affects ash_ai: from 0.6.0 before 1.0.0.
Severity
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-31 16:05 UTC
CWE
- CWE-835 - Loop with Unreachable Exit Condition ('Infinite Loop')
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/ash-project/ash_ai/security/ad… | vendor-advisoryrelated |
| https://cna.erlef.org/cves/CVE-2026-82579.html | related |
| https://osv.dev/vulnerability/EEF-CVE-2026-82579 | related |
| https://github.com/ash-project/ash_ai/commit/5332… | patch |
Impacted products
2 products
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| ash-project | ash_ai |
Affected:
0.6.0 , < 1.0.0
(semver)
cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:* |
||
| ash-project | ash_ai |
Affected:
bc2122f78fca6c11d8ec2b9ac53148ec17476460 , < 53325fdab90afab628c6a53232ef2a9001580bd9
(git)
cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:* |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-82579",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-31T16:05:35.220018Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-31T16:05:58.542Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/ash-project/ash_ai/security/advisories/GHSA-rcx7-x2w5-mmc2"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"collectionURL": "https://repo.hex.pm",
"cpes": [
"cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unaffected",
"modules": [
"\u0027Elixir.AshAi.ToolLoop\u0027"
],
"packageName": "ash_ai",
"packageURL": "pkg:hex/ash_ai",
"product": "ash_ai",
"programFiles": [
"lib/ash_ai/tool_loop.ex"
],
"programRoutines": [
{
"name": "\u0027Elixir.AshAi.ToolLoop\u0027:run/2"
},
{
"name": "\u0027Elixir.AshAi.ToolLoop\u0027:stream/2"
}
],
"repo": "https://github.com/ash-project/ash_ai",
"vendor": "ash-project",
"versions": [
{
"lessThan": "1.0.0",
"status": "affected",
"version": "0.6.0",
"versionType": "semver"
}
]
},
{
"collectionURL": "https://github.com",
"cpes": [
"cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unaffected",
"modules": [
"\u0027Elixir.AshAi.ToolLoop\u0027"
],
"packageName": "ash-project/ash_ai",
"packageURL": "pkg:github/ash-project/ash_ai",
"product": "ash_ai",
"programFiles": [
"lib/ash_ai/tool_loop.ex"
],
"programRoutines": [
{
"name": "\u0027Elixir.AshAi.ToolLoop\u0027:run/2"
},
{
"name": "\u0027Elixir.AshAi.ToolLoop\u0027:stream/2"
}
],
"repo": "https://github.com/ash-project/ash_ai",
"vendor": "ash-project",
"versions": [
{
"lessThan": "53325fdab90afab628c6a53232ef2a9001580bd9",
"status": "affected",
"version": "bc2122f78fca6c11d8ec2b9ac53148ec17476460",
"versionType": "git"
}
]
}
],
"cpeApplicability": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*",
"versionEndExcluding": "1.0.0",
"versionStartIncluding": "0.6.0",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
],
"operator": "AND"
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Peter Ullrich"
},
{
"lang": "en",
"type": "reporter",
"value": "Peter Ullrich"
},
{
"lang": "en",
"type": "remediation developer",
"value": "Zach Daniel / Ash Project"
},
{
"lang": "en",
"type": "coordinator",
"value": "Jonatan M\u00e4nnchen / EEF"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cp\u003eLoop with Unreachable Exit Condition (Infinite Loop) vulnerability in ash-project ash_ai allows an attacker who can influence a model\u0027s output to hang the tool loop and drive unbounded, repeated model requests.\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003eAshAi.ToolLoop\u003c/code\u003e classifies a model response of \u003ccode\u003e:tool_calls\u003c/code\u003e, then filters the calls through \u003ccode\u003enormalize_tool_calls/2\u003c/code\u003e and \u003ccode\u003eunprocessed_tool_calls/2\u003c/code\u003e. Both can empty the list: a call missing a valid name, or one reusing a \u003ccode\u003etool_call_id\u003c/code\u003e that already has a result in history, is dropped. With an empty list the loop appended nothing and recursed with a byte-identical message list, so the conversation never advanced and the same request was re-sent every iteration. Under the supported \u003ccode\u003emax_iterations: :infinity\u003c/code\u003e this never terminated; otherwise it exhausted the full budget. Prompt-injected content can make the model re-emit a spent \u003ccode\u003etool_call_id\u003c/code\u003e. The fix treats an empty post-filter list as terminal.\u003c/p\u003e\n\u003cp\u003eThis issue affects ash_ai: from 0.6.0 before 1.0.0.\u003c/p\u003e"
},
{
"base64": false,
"type": "text/markdown",
"value": "Loop with Unreachable Exit Condition (Infinite Loop) vulnerability in ash-project ash_ai allows an attacker who can influence a model\u0027s output to hang the tool loop and drive unbounded, repeated model requests.\n\n`AshAi.ToolLoop` classifies a model response of `:tool_calls`, then filters the calls through `normalize_tool_calls/2` and `unprocessed_tool_calls/2`. Both can empty the list: a call missing a valid name, or one reusing a `tool_call_id` that already has a result in history, is dropped. With an empty list the loop appended nothing and recursed with a byte-identical message list, so the conversation never advanced and the same request was re-sent every iteration. Under the supported `max_iterations: :infinity` this never terminated; otherwise it exhausted the full budget. Prompt-injected content can make the model re-emit a spent `tool_call_id`. The fix treats an empty post-filter list as terminal.\n\nThis issue affects ash_ai: from 0.6.0 before 1.0.0."
}
],
"value": "Loop with Unreachable Exit Condition (Infinite Loop) vulnerability in ash-project ash_ai allows an attacker who can influence a model\u0027s output to hang the tool loop and drive unbounded, repeated model requests.\n\nAshAi.ToolLoop classifies a model response of :tool_calls, then filters the calls through normalize_tool_calls/2 and unprocessed_tool_calls/2. Both can empty the list: a call missing a valid name, or one reusing a tool_call_id that already has a result in history, is dropped. With an empty list the loop appended nothing and recursed with a byte-identical message list, so the conversation never advanced and the same request was re-sent every iteration. Under the supported max_iterations: :infinity this never terminated; otherwise it exhausted the full budget. Prompt-injected content can make the model re-emit a spent tool_call_id. The fix treats an empty post-filter list as terminal.\n\nThis issue affects ash_ai: from 0.6.0 before 1.0.0."
}
],
"impacts": [
{
"capecId": "CAPEC-130",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-130 Excessive Allocation"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "PRESENT",
"attackVector": "NETWORK",
"baseScore": 6,
"baseSeverity": "MEDIUM",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "NONE",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-835",
"description": "CWE-835 Loop with Unreachable Exit Condition (\u0027Infinite Loop\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-31T01:07:49.185Z",
"orgId": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
"shortName": "EEF"
},
"references": [
{
"tags": [
"vendor-advisory",
"related"
],
"url": "https://github.com/ash-project/ash_ai/security/advisories/GHSA-rcx7-x2w5-mmc2"
},
{
"tags": [
"related"
],
"url": "https://cna.erlef.org/cves/CVE-2026-82579.html"
},
{
"tags": [
"related"
],
"url": "https://osv.dev/vulnerability/EEF-CVE-2026-82579"
},
{
"tags": [
"patch"
],
"url": "https://github.com/ash-project/ash_ai/commit/53325fdab90afab628c6a53232ef2a9001580bd9"
}
],
"source": {
"discovery": "EXTERNAL"
},
"title": "AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service"
}
},
"cveMetadata": {
"assignerOrgId": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
"assignerShortName": "EEF",
"cveId": "CVE-2026-82579",
"datePublished": "2026-08-31T01:07:49.185Z",
"dateReserved": "2026-08-30T20:00:01.852Z",
"dateUpdated": "2026-08-31T16:05:58.542Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-82579",
"date": "2026-09-19",
"epss": "0.00268",
"percentile": "0.19228"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"collectionURL": "https://repo.hex.pm",
"cpes": [
"cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unaffected",
"modules": [
"\u0027Elixir.AshAi.ToolLoop\u0027"
],
"packageName": "ash_ai",
"packageURL": "pkg:hex/ash_ai",
"product": "ash_ai",
"programFiles": [
"lib/ash_ai/tool_loop.ex"
],
"programRoutines": [
{
"name": "\u0027Elixir.AshAi.ToolLoop\u0027:run/2"
},
{
"name": "\u0027Elixir.AshAi.ToolLoop\u0027:stream/2"
}
],
"repo": "https://github.com/ash-project/ash_ai",
"vendor": "ash-project",
"versions": [
{
"lessThan": "1.0.0",
"status": "affected",
"version": "0.6.0",
"versionType": "semver"
}
]
},
{
"collectionURL": "https://github.com",
"cpes": [
"cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unaffected",
"modules": [
"\u0027Elixir.AshAi.ToolLoop\u0027"
],
"packageName": "ash-project/ash_ai",
"packageURL": "pkg:github/ash-project/ash_ai",
"product": "ash_ai",
"programFiles": [
"lib/ash_ai/tool_loop.ex"
],
"programRoutines": [
{
"name": "\u0027Elixir.AshAi.ToolLoop\u0027:run/2"
},
{
"name": "\u0027Elixir.AshAi.ToolLoop\u0027:stream/2"
}
],
"repo": "https://github.com/ash-project/ash_ai",
"vendor": "ash-project",
"versions": [
{
"lessThan": "53325fdab90afab628c6a53232ef2a9001580bd9",
"status": "affected",
"version": "bc2122f78fca6c11d8ec2b9ac53148ec17476460",
"versionType": "git"
}
]
}
],
"source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db"
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "Loop with Unreachable Exit Condition (Infinite Loop) vulnerability in ash-project ash_ai allows an attacker who can influence a model\u0027s output to hang the tool loop and drive unbounded, repeated model requests.\n\nAshAi.ToolLoop classifies a model response of :tool_calls, then filters the calls through normalize_tool_calls/2 and unprocessed_tool_calls/2. Both can empty the list: a call missing a valid name, or one reusing a tool_call_id that already has a result in history, is dropped. With an empty list the loop appended nothing and recursed with a byte-identical message list, so the conversation never advanced and the same request was re-sent every iteration. Under the supported max_iterations: :infinity this never terminated; otherwise it exhausted the full budget. Prompt-injected content can make the model re-emit a spent tool_call_id. The fix treats an empty post-filter list as terminal.\n\nThis issue affects ash_ai: from 0.6.0 before 1.0.0."
}
],
"id": "CVE-2026-82579",
"lastModified": "2026-09-01T21:15:00.147",
"metrics": {
"cvssMetricV40": [
{
"cvssData": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "PRESENT",
"attackVector": "NETWORK",
"availabilityRequirement": "NOT_DEFINED",
"baseScore": 6.0,
"baseSeverity": "MEDIUM",
"confidentialityRequirement": "NOT_DEFINED",
"exploitMaturity": "NOT_DEFINED",
"integrityRequirement": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "NONE",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-82579",
"options": [
{
"exploitation": "poc"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-31T16:05:35.220018Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-08-31T02:17:02.270",
"references": [
{
"source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
"url": "https://cna.erlef.org/cves/CVE-2026-82579.html"
},
{
"source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
"url": "https://github.com/ash-project/ash_ai/commit/53325fdab90afab628c6a53232ef2a9001580bd9"
},
{
"source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
"url": "https://github.com/ash-project/ash_ai/security/advisories/GHSA-rcx7-x2w5-mmc2"
},
{
"source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
"url": "https://osv.dev/vulnerability/EEF-CVE-2026-82579"
},
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"url": "https://github.com/ash-project/ash_ai/security/advisories/GHSA-rcx7-x2w5-mmc2"
}
],
"sourceIdentifier": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
"vulnStatus": "Deferred",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-835"
}
],
"source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
"type": "Secondary"
}
]
}
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-82579",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-31T16:05:35.220018Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-31T16:05:53.304Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/ash-project/ash_ai/security/advisories/GHSA-rcx7-x2w5-mmc2"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"collectionURL": "https://repo.hex.pm",
"cpes": [
"cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unaffected",
"modules": [
"\u0027Elixir.AshAi.ToolLoop\u0027"
],
"packageName": "ash_ai",
"packageURL": "pkg:hex/ash_ai",
"product": "ash_ai",
"programFiles": [
"lib/ash_ai/tool_loop.ex"
],
"programRoutines": [
{
"name": "\u0027Elixir.AshAi.ToolLoop\u0027:run/2"
},
{
"name": "\u0027Elixir.AshAi.ToolLoop\u0027:stream/2"
}
],
"repo": "https://github.com/ash-project/ash_ai",
"vendor": "ash-project",
"versions": [
{
"lessThan": "1.0.0",
"status": "affected",
"version": "0.6.0",
"versionType": "semver"
}
]
},
{
"collectionURL": "https://github.com",
"cpes": [
"cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unaffected",
"modules": [
"\u0027Elixir.AshAi.ToolLoop\u0027"
],
"packageName": "ash-project/ash_ai",
"packageURL": "pkg:github/ash-project/ash_ai",
"product": "ash_ai",
"programFiles": [
"lib/ash_ai/tool_loop.ex"
],
"programRoutines": [
{
"name": "\u0027Elixir.AshAi.ToolLoop\u0027:run/2"
},
{
"name": "\u0027Elixir.AshAi.ToolLoop\u0027:stream/2"
}
],
"repo": "https://github.com/ash-project/ash_ai",
"vendor": "ash-project",
"versions": [
{
"lessThan": "53325fdab90afab628c6a53232ef2a9001580bd9",
"status": "affected",
"version": "bc2122f78fca6c11d8ec2b9ac53148ec17476460",
"versionType": "git"
}
]
}
],
"cpeApplicability": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*",
"versionEndExcluding": "1.0.0",
"versionStartIncluding": "0.6.0",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
],
"operator": "AND"
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Peter Ullrich"
},
{
"lang": "en",
"type": "reporter",
"value": "Peter Ullrich"
},
{
"lang": "en",
"type": "remediation developer",
"value": "Zach Daniel / Ash Project"
},
{
"lang": "en",
"type": "coordinator",
"value": "Jonatan M\u00e4nnchen / EEF"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cp\u003eLoop with Unreachable Exit Condition (Infinite Loop) vulnerability in ash-project ash_ai allows an attacker who can influence a model\u0027s output to hang the tool loop and drive unbounded, repeated model requests.\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003eAshAi.ToolLoop\u003c/code\u003e classifies a model response of \u003ccode\u003e:tool_calls\u003c/code\u003e, then filters the calls through \u003ccode\u003enormalize_tool_calls/2\u003c/code\u003e and \u003ccode\u003eunprocessed_tool_calls/2\u003c/code\u003e. Both can empty the list: a call missing a valid name, or one reusing a \u003ccode\u003etool_call_id\u003c/code\u003e that already has a result in history, is dropped. With an empty list the loop appended nothing and recursed with a byte-identical message list, so the conversation never advanced and the same request was re-sent every iteration. Under the supported \u003ccode\u003emax_iterations: :infinity\u003c/code\u003e this never terminated; otherwise it exhausted the full budget. Prompt-injected content can make the model re-emit a spent \u003ccode\u003etool_call_id\u003c/code\u003e. The fix treats an empty post-filter list as terminal.\u003c/p\u003e\n\u003cp\u003eThis issue affects ash_ai: from 0.6.0 before 1.0.0.\u003c/p\u003e"
},
{
"base64": false,
"type": "text/markdown",
"value": "Loop with Unreachable Exit Condition (Infinite Loop) vulnerability in ash-project ash_ai allows an attacker who can influence a model\u0027s output to hang the tool loop and drive unbounded, repeated model requests.\n\n`AshAi.ToolLoop` classifies a model response of `:tool_calls`, then filters the calls through `normalize_tool_calls/2` and `unprocessed_tool_calls/2`. Both can empty the list: a call missing a valid name, or one reusing a `tool_call_id` that already has a result in history, is dropped. With an empty list the loop appended nothing and recursed with a byte-identical message list, so the conversation never advanced and the same request was re-sent every iteration. Under the supported `max_iterations: :infinity` this never terminated; otherwise it exhausted the full budget. Prompt-injected content can make the model re-emit a spent `tool_call_id`. The fix treats an empty post-filter list as terminal.\n\nThis issue affects ash_ai: from 0.6.0 before 1.0.0."
}
],
"value": "Loop with Unreachable Exit Condition (Infinite Loop) vulnerability in ash-project ash_ai allows an attacker who can influence a model\u0027s output to hang the tool loop and drive unbounded, repeated model requests.\n\nAshAi.ToolLoop classifies a model response of :tool_calls, then filters the calls through normalize_tool_calls/2 and unprocessed_tool_calls/2. Both can empty the list: a call missing a valid name, or one reusing a tool_call_id that already has a result in history, is dropped. With an empty list the loop appended nothing and recursed with a byte-identical message list, so the conversation never advanced and the same request was re-sent every iteration. Under the supported max_iterations: :infinity this never terminated; otherwise it exhausted the full budget. Prompt-injected content can make the model re-emit a spent tool_call_id. The fix treats an empty post-filter list as terminal.\n\nThis issue affects ash_ai: from 0.6.0 before 1.0.0."
}
],
"impacts": [
{
"capecId": "CAPEC-130",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-130 Excessive Allocation"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "PRESENT",
"attackVector": "NETWORK",
"baseScore": 6,
"baseSeverity": "MEDIUM",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "NONE",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-835",
"description": "CWE-835 Loop with Unreachable Exit Condition (\u0027Infinite Loop\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-31T01:07:49.185Z",
"orgId": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
"shortName": "EEF"
},
"references": [
{
"tags": [
"vendor-advisory",
"related"
],
"url": "https://github.com/ash-project/ash_ai/security/advisories/GHSA-rcx7-x2w5-mmc2"
},
{
"tags": [
"related"
],
"url": "https://cna.erlef.org/cves/CVE-2026-82579.html"
},
{
"tags": [
"related"
],
"url": "https://osv.dev/vulnerability/EEF-CVE-2026-82579"
},
{
"tags": [
"patch"
],
"url": "https://github.com/ash-project/ash_ai/commit/53325fdab90afab628c6a53232ef2a9001580bd9"
}
],
"source": {
"discovery": "EXTERNAL"
},
"title": "AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service"
}
},
"cveMetadata": {
"assignerOrgId": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
"assignerShortName": "EEF",
"cveId": "CVE-2026-82579",
"datePublished": "2026-08-31T01:07:49.185Z",
"dateReserved": "2026-08-30T20:00:01.852Z",
"dateUpdated": "2026-08-31T16:05:58.542Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Loading…
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.
Loading…