CVE-2023-37275 (GCVE-0-2023-37275)

Vulnerability from cvelistv5 – Published: 2023-07-13 22:34 – Updated: 2024-10-22 14:52
VLAI?
Title
System logs spoofable in Auto-GPT via ANSI control sequences
Summary
Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to review and control which commands should be executed. Before v0.4.3, it was possible for a malicious external resource (such as a website browsed by Auto-GPT) to cause misleading messages to be printed to the console by getting the LLM to regurgitate JSON encoded ANSI escape sequences (`\u001b[`). These escape sequences were JSON decoded and printed to the console as part of the model's "thinking process". The issue has been patched in release version 0.4.3.
Severity ?
3.1 (Low)
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:N
CWE
  • CWE-117 - Improper Output Neutralization for Logs
Assigner
References
Impacted products
Vendor Product Version
Significant-Gravitas Auto-GPT Affected: < 0.4.3
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "providerMetadata": {
          "dateUpdated": "2024-08-02T17:09:33.632Z",
          "orgId": "af854a3a-2127-422b-91ae-364da2661108",
          "shortName": "CVE"
        },
        "references": [
          {
            "name": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh",
            "tags": [
              "x_refsource_CONFIRM",
              "x_transferred"
            ],
            "url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh"
          },
          {
            "name": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4810",
            "tags": [
              "x_refsource_MISC",
              "x_transferred"
            ],
            "url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4810"
          }
        ],
        "title": "CVE Program Container"
      },
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2023-37275",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2024-10-22T14:51:38.896286Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2024-10-22T14:52:38.684Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "Auto-GPT",
          "vendor": "Significant-Gravitas",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.4.3"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to review and control which commands should be executed. Before v0.4.3, it was possible for a malicious external resource (such as a website browsed by Auto-GPT) to cause misleading messages to be printed to the console by getting the LLM to regurgitate JSON encoded ANSI escape sequences (`\\u001b[`). These escape sequences were JSON decoded and printed to the console as part of the model\u0027s \"thinking process\". The issue has been patched in release version 0.4.3.\n"
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 3.1,
            "baseSeverity": "LOW",
            "confidentialityImpact": "NONE",
            "integrityImpact": "LOW",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-117",
              "description": "CWE-117: Improper Output Neutralization for Logs",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2023-07-13T22:34:45.809Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh"
        },
        {
          "name": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4810",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/Significant-Gravitas/Auto-GPT/pull/4810"
        }
      ],
      "source": {
        "advisory": "GHSA-r7f7-qrrv-3fjh",
        "discovery": "UNKNOWN"
      },
      "title": "System logs spoofable in Auto-GPT via ANSI control sequences"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2023-37275",
    "datePublished": "2023-07-13T22:34:45.809Z",
    "dateReserved": "2023-06-29T19:35:26.440Z",
    "dateUpdated": "2024-10-22T14:52:38.684Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1",
  "vulnerability-lookup:meta": {
    "fkie_nvd": {
      "configurations": "[{\"nodes\": [{\"operator\": \"OR\", \"negate\": false, \"cpeMatch\": [{\"vulnerable\": true, \"criteria\": \"cpe:2.3:a:agpt:auto-gpt:*:*:*:*:*:*:*:*\", \"versionEndExcluding\": \"0.4.3\", \"matchCriteriaId\": \"10E8D9E9-E73C-4B20-989E-1D432F7ED3BB\"}]}]}]",
      "descriptions": "[{\"lang\": \"en\", \"value\": \"Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to review and control which commands should be executed. Before v0.4.3, it was possible for a malicious external resource (such as a website browsed by Auto-GPT) to cause misleading messages to be printed to the console by getting the LLM to regurgitate JSON encoded ANSI escape sequences (`\\\\u001b[`). These escape sequences were JSON decoded and printed to the console as part of the model\u0027s \\\"thinking process\\\". The issue has been patched in release version 0.4.3.\\n\"}]",
      "id": "CVE-2023-37275",
      "lastModified": "2024-11-21T08:11:22.443",
      "metrics": "{\"cvssMetricV31\": [{\"source\": \"security-advisories@github.com\", \"type\": \"Secondary\", \"cvssData\": {\"version\": \"3.1\", \"vectorString\": \"CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:N\", \"baseScore\": 3.1, \"baseSeverity\": \"LOW\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"userInteraction\": \"REQUIRED\", \"scope\": \"UNCHANGED\", \"confidentialityImpact\": \"NONE\", \"integrityImpact\": \"LOW\", \"availabilityImpact\": \"NONE\"}, \"exploitabilityScore\": 1.6, \"impactScore\": 1.4}, {\"source\": \"nvd@nist.gov\", \"type\": \"Primary\", \"cvssData\": {\"version\": \"3.1\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N\", \"baseScore\": 4.3, \"baseSeverity\": \"MEDIUM\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"LOW\", \"privilegesRequired\": \"NONE\", \"userInteraction\": \"REQUIRED\", \"scope\": \"UNCHANGED\", \"confidentialityImpact\": \"NONE\", \"integrityImpact\": \"LOW\", \"availabilityImpact\": \"NONE\"}, \"exploitabilityScore\": 2.8, \"impactScore\": 1.4}]}",
      "published": "2023-07-13T23:15:10.890",
      "references": "[{\"url\": \"https://github.com/Significant-Gravitas/Auto-GPT/pull/4810\", \"source\": \"security-advisories@github.com\", \"tags\": [\"Patch\", \"Third Party Advisory\"]}, {\"url\": \"https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh\", \"source\": \"security-advisories@github.com\", \"tags\": [\"Patch\", \"Third Party Advisory\"]}, {\"url\": \"https://github.com/Significant-Gravitas/Auto-GPT/pull/4810\", \"source\": \"af854a3a-2127-422b-91ae-364da2661108\", \"tags\": [\"Patch\", \"Third Party Advisory\"]}, {\"url\": \"https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh\", \"source\": \"af854a3a-2127-422b-91ae-364da2661108\", \"tags\": [\"Patch\", \"Third Party Advisory\"]}]",
      "sourceIdentifier": "security-advisories@github.com",
      "vulnStatus": "Modified",
      "weaknesses": "[{\"source\": \"security-advisories@github.com\", \"type\": \"Primary\", \"description\": [{\"lang\": \"en\", \"value\": \"CWE-117\"}]}]"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2023-37275\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2023-07-13T23:15:10.890\",\"lastModified\":\"2024-11-21T08:11:22.443\",\"vulnStatus\":\"Modified\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to review and control which commands should be executed. Before v0.4.3, it was possible for a malicious external resource (such as a website browsed by Auto-GPT) to cause misleading messages to be printed to the console by getting the LLM to regurgitate JSON encoded ANSI escape sequences (`\\\\u001b[`). These escape sequences were JSON decoded and printed to the console as part of the model\u0027s \\\"thinking process\\\". The issue has been patched in release version 0.4.3.\\n\"}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:N\",\"baseScore\":3.1,\"baseSeverity\":\"LOW\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"HIGH\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"NONE\",\"integrityImpact\":\"LOW\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":1.6,\"impactScore\":1.4},{\"source\":\"nvd@nist.gov\",\"type\":\"Primary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N\",\"baseScore\":4.3,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"NONE\",\"integrityImpact\":\"LOW\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":2.8,\"impactScore\":1.4}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-117\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:agpt:auto-gpt:*:*:*:*:*:*:*:*\",\"versionEndExcluding\":\"0.4.3\",\"matchCriteriaId\":\"10E8D9E9-E73C-4B20-989E-1D432F7ED3BB\"}]}]}],\"references\":[{\"url\":\"https://github.com/Significant-Gravitas/Auto-GPT/pull/4810\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Patch\",\"Third Party Advisory\"]},{\"url\":\"https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Patch\",\"Third Party Advisory\"]},{\"url\":\"https://github.com/Significant-Gravitas/Auto-GPT/pull/4810\",\"source\":\"af854a3a-2127-422b-91ae-364da2661108\",\"tags\":[\"Patch\",\"Third Party Advisory\"]},{\"url\":\"https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh\",\"source\":\"af854a3a-2127-422b-91ae-364da2661108\",\"tags\":[\"Patch\",\"Third Party Advisory\"]}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CVE Program Container\", \"references\": [{\"url\": \"https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh\", \"name\": \"https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh\", \"tags\": [\"x_refsource_CONFIRM\", \"x_transferred\"]}, {\"url\": \"https://github.com/Significant-Gravitas/Auto-GPT/pull/4810\", \"name\": \"https://github.com/Significant-Gravitas/Auto-GPT/pull/4810\", \"tags\": [\"x_refsource_MISC\", \"x_transferred\"]}], \"providerMetadata\": {\"orgId\": \"af854a3a-2127-422b-91ae-364da2661108\", \"shortName\": \"CVE\", \"dateUpdated\": \"2024-08-02T17:09:33.632Z\"}}, {\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2023-37275\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2024-10-22T14:51:38.896286Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2024-10-22T14:52:34.182Z\"}}], \"cna\": {\"title\": \"System logs spoofable in Auto-GPT via ANSI control sequences\", \"source\": {\"advisory\": \"GHSA-r7f7-qrrv-3fjh\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 3.1, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"LOW\", \"vectorString\": \"CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:N\", \"integrityImpact\": \"LOW\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"HIGH\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"NONE\"}}], \"affected\": [{\"vendor\": \"Significant-Gravitas\", \"product\": \"Auto-GPT\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 0.4.3\"}]}], \"references\": [{\"url\": \"https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh\", \"name\": \"https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-r7f7-qrrv-3fjh\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/Significant-Gravitas/Auto-GPT/pull/4810\", \"name\": \"https://github.com/Significant-Gravitas/Auto-GPT/pull/4810\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to review and control which commands should be executed. Before v0.4.3, it was possible for a malicious external resource (such as a website browsed by Auto-GPT) to cause misleading messages to be printed to the console by getting the LLM to regurgitate JSON encoded ANSI escape sequences (`\\\\u001b[`). These escape sequences were JSON decoded and printed to the console as part of the model\u0027s \\\"thinking process\\\". The issue has been patched in release version 0.4.3.\\n\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-117\", \"description\": \"CWE-117: Improper Output Neutralization for Logs\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2023-07-13T22:34:45.809Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2023-37275\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2024-10-22T14:52:38.684Z\", \"dateReserved\": \"2023-06-29T19:35:26.440Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2023-07-13T22:34:45.809Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.1"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

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.