CVE-2026-33233 (GCVE-0-2026-33233)

Vulnerability from cvelistv5 – Published: 2026-05-19 00:46 – Updated: 2026-05-19 13:42
VLAI
Title
AutoGPT Platform: Remote Code Execution via Unsafe Pickle Deserialization of Redis Cache Entries
Summary
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.6.34 through 0.6.51, the backend deserializes Redis cache bytes using pickle.loads without integrity/authenticity checks. The write path serializes values with pickle.dumps(...) into Redis and the read path blindly invokes pickle.loads(...) on bytes with no HMAC/signature or strict schema validation gating deserialization. If an attacker can poison a shared-cache key in Redis, arbitrary command execution is possible in the backend container context, affecting confidentiality, integrity, and availability. This issue has been fixed in version 0.6.52.
Severity
7.6 (High)
CVSS:3.1/AV:A/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H
SSVC
Exploitation: poc Automatable: no Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
  • CWE-502 - Deserialization of Untrusted Data
  • CWE-345 - Insufficient Verification of Data Authenticity
  • CWE-94 - Improper Control of Generation of Code ('Code Injection')
Assigner
References
Impacted products
Vendor Product Version
Significant-Gravitas AutoGPT Affected: >= 0.6.34, < 0.6.52
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-33233",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-19T12:55:46.776124Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-19T13:42:05.971Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37xq-w4m9"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "AutoGPT",
          "vendor": "Significant-Gravitas",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.6.34, \u003c 0.6.52"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.6.34 through 0.6.51, the backend deserializes Redis cache bytes using pickle.loads without integrity/authenticity checks. The write path serializes values with pickle.dumps(...) into Redis and the read path blindly invokes pickle.loads(...) on bytes with no HMAC/signature or strict schema validation gating deserialization. If an attacker can poison a shared-cache key in Redis, arbitrary command execution is possible in the backend container context, affecting confidentiality, integrity, and availability. This issue has been fixed in version 0.6.52."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "ADJACENT_NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 7.6,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "HIGH",
            "scope": "CHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:A/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-502",
              "description": "CWE-502: Deserialization of Untrusted Data",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-345",
              "description": "CWE-345: Insufficient Verification of Data Authenticity",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-94",
              "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-19T00:46:49.642Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37xq-w4m9",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37xq-w4m9"
        },
        {
          "name": "https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52"
        }
      ],
      "source": {
        "advisory": "GHSA-rfg2-37xq-w4m9",
        "discovery": "UNKNOWN"
      },
      "title": "AutoGPT Platform: Remote Code Execution via Unsafe Pickle Deserialization of Redis Cache Entries"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-33233",
    "datePublished": "2026-05-19T00:46:49.642Z",
    "dateReserved": "2026-03-18T02:42:27.507Z",
    "dateUpdated": "2026-05-19T13:42:05.971Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-33233",
      "date": "2026-06-07",
      "epss": "0.00015",
      "percentile": "0.03425"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-33233\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-05-19T02:16:15.840\",\"lastModified\":\"2026-05-19T15:16:30.033\",\"vulnStatus\":\"Deferred\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.6.34 through 0.6.51, the backend deserializes Redis cache bytes using pickle.loads without integrity/authenticity checks. The write path serializes values with pickle.dumps(...) into Redis and the read path blindly invokes pickle.loads(...) on bytes with no HMAC/signature or strict schema validation gating deserialization. If an attacker can poison a shared-cache key in Redis, arbitrary command execution is possible in the backend container context, affecting confidentiality, integrity, and availability. This issue has been fixed in version 0.6.52.\"}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:A/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H\",\"baseScore\":7.6,\"baseSeverity\":\"HIGH\",\"attackVector\":\"ADJACENT_NETWORK\",\"attackComplexity\":\"HIGH\",\"privilegesRequired\":\"HIGH\",\"userInteraction\":\"NONE\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":1.0,\"impactScore\":6.0}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-94\"},{\"lang\":\"en\",\"value\":\"CWE-345\"},{\"lang\":\"en\",\"value\":\"CWE-502\"}]}],\"references\":[{\"url\":\"https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37xq-w4m9\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37xq-w4m9\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-33233\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-05-19T12:55:46.776124Z\"}}}], \"references\": [{\"url\": \"https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37xq-w4m9\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-05-19T12:56:28.581Z\"}}], \"cna\": {\"title\": \"AutoGPT Platform: Remote Code Execution via Unsafe Pickle Deserialization of Redis Cache Entries\", \"source\": {\"advisory\": \"GHSA-rfg2-37xq-w4m9\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"CHANGED\", \"version\": \"3.1\", \"baseScore\": 7.6, \"attackVector\": \"ADJACENT_NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:A/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"HIGH\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"HIGH\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"Significant-Gravitas\", \"product\": \"AutoGPT\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003e= 0.6.34, \u003c 0.6.52\"}]}], \"references\": [{\"url\": \"https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37xq-w4m9\", \"name\": \"https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37xq-w4m9\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52\", \"name\": \"https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.6.34 through 0.6.51, the backend deserializes Redis cache bytes using pickle.loads without integrity/authenticity checks. The write path serializes values with pickle.dumps(...) into Redis and the read path blindly invokes pickle.loads(...) on bytes with no HMAC/signature or strict schema validation gating deserialization. If an attacker can poison a shared-cache key in Redis, arbitrary command execution is possible in the backend container context, affecting confidentiality, integrity, and availability. This issue has been fixed in version 0.6.52.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-502\", \"description\": \"CWE-502: Deserialization of Untrusted Data\"}]}, {\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-345\", \"description\": \"CWE-345: Insufficient Verification of Data Authenticity\"}]}, {\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-94\", \"description\": \"CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-05-19T00:46:49.642Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-33233\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-05-19T13:42:05.971Z\", \"dateReserved\": \"2026-03-18T02:42:27.507Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-05-19T00:46:49.642Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





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.


Detection rules are retrieved from Rulezet.