CVE-2026-48116 (GCVE-0-2026-48116)

Vulnerability from cvelistv5 – Published: 2026-05-28 21:19 – Updated: 2026-05-30 02:22
VLAI
Title
AnythingLLM: RCE via ripgrep --pre argument injection in filesystem-search-files agent skill
Summary
AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. Prior to 1.13.0, the filesystem-search-files agent skill passes its LLM-controlled pattern parameter to ripgrep as a positional argument without a -- end-of-options separator. ripgrep parses any argument that starts with - as an option, so a pattern of --pre=/bin/sh turns ripgrep into a script executor: it runs /bin/sh <file> for every file it walks. An attacker who can chat with an agent on a deployment with the filesystem plugin enabled (the default in the official Docker image) can use this, together with the sibling filesystem-write-text-file skill, to run arbitrary commands inside the AnythingLLM server container. This vulnerability is fixed in 1.13.0.
Severity
7.5 (High)
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
SSVC
Exploitation: poc Automatable: no Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
  • CWE-77 - Improper Neutralization of Special Elements used in a Command ('Command Injection')
  • CWE-88 - Improper Neutralization of Argument Delimiters in a Command ('Argument Injection')
Assigner
References
Impacted products
Vendor Product Version
Mintplex-Labs anything-llm Affected: < 1.13.0
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-48116",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-30T02:22:29.307430Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-30T02:22:53.743Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "anything-llm",
          "vendor": "Mintplex-Labs",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 1.13.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. Prior to 1.13.0, the filesystem-search-files agent skill passes its LLM-controlled pattern parameter to ripgrep as a positional argument without a -- end-of-options separator. ripgrep parses any argument that starts with - as an option, so a pattern of --pre=/bin/sh turns ripgrep into a script executor: it runs /bin/sh \u003cfile\u003e for every file it walks. An attacker who can chat with an agent on a deployment with the filesystem plugin enabled (the default in the official Docker image) can use this, together with the sibling filesystem-write-text-file skill, to run arbitrary commands inside the AnythingLLM server container. This vulnerability is fixed in 1.13.0."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 7.5,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-77",
              "description": "CWE-77: Improper Neutralization of Special Elements used in a Command (\u0027Command Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-88",
              "description": "CWE-88: Improper Neutralization of Argument Delimiters in a Command (\u0027Argument Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-28T21:19:51.965Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59"
        },
        {
          "name": "https://github.com/Mintplex-Labs/anything-llm/commit/94ed62d320df1a06c229e4bc3ee09c2cb5111b33",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/Mintplex-Labs/anything-llm/commit/94ed62d320df1a06c229e4bc3ee09c2cb5111b33"
        }
      ],
      "source": {
        "advisory": "GHSA-6hrp-7mw6-8v59",
        "discovery": "UNKNOWN"
      },
      "title": "AnythingLLM: RCE via ripgrep --pre argument injection in filesystem-search-files agent skill"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-48116",
    "datePublished": "2026-05-28T21:19:51.965Z",
    "dateReserved": "2026-05-20T18:46:58.289Z",
    "dateUpdated": "2026-05-30T02:22:53.743Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-48116",
      "date": "2026-07-21",
      "epss": "0.00366",
      "percentile": "0.28988"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-48116\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-05-28T22:17:01.390\",\"lastModified\":\"2026-07-21T10:10:00.103\",\"vulnStatus\":\"Modified\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. Prior to 1.13.0, the filesystem-search-files agent skill passes its LLM-controlled pattern parameter to ripgrep as a positional argument without a -- end-of-options separator. ripgrep parses any argument that starts with - as an option, so a pattern of --pre=/bin/sh turns ripgrep into a script executor: it runs /bin/sh \u003cfile\u003e for every file it walks. An attacker who can chat with an agent on a deployment with the filesystem plugin enabled (the default in the official Docker image) can use this, together with the sibling filesystem-write-text-file skill, to run arbitrary commands inside the AnythingLLM server container. This vulnerability is fixed in 1.13.0.\"},{\"lang\":\"es\",\"value\":\"AnythingLLM es una aplicaci\u00f3n que convierte fragmentos de contenido en contexto que cualquier LLM puede usar como referencias durante el chat. Antes de la versi\u00f3n 1.13.0, la habilidad del agente filesystem-search-files pasa su par\u00e1metro de patr\u00f3n controlado por LLM a ripgrep como un argumento posicional sin un separador de fin de opciones --. ripgrep analiza cualquier argumento que comienza con - como una opci\u00f3n, por lo que un patr\u00f3n de --pre=/bin/sh convierte a ripgrep en un ejecutor de scripts: ejecuta /bin/sh \u003cfile\u003e para cada archivo que recorre. Un atacante que puede chatear con un agente en una implementaci\u00f3n con el plugin de sistema de archivos habilitado (el valor predeterminado en la imagen oficial de Docker) puede usar esto, junto con la habilidad hermana filesystem-write-text-file, para ejecutar comandos arbitrarios dentro del contenedor del servidor de AnythingLLM. Esta vulnerabilidad est\u00e1 corregida en la versi\u00f3n 1.13.0.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"Mintplex-Labs\",\"product\":\"anything-llm\",\"versions\":[{\"version\":\"\u003c 1.13.0\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H\",\"baseScore\":7.5,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"HIGH\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":1.6,\"impactScore\":5.9},{\"source\":\"nvd@nist.gov\",\"type\":\"Primary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H\",\"baseScore\":8.8,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":2.8,\"impactScore\":5.9}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-05-30T02:22:29.307430Z\",\"id\":\"CVE-2026-48116\",\"options\":[{\"exploitation\":\"poc\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-77\"},{\"lang\":\"en\",\"value\":\"CWE-88\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:mintplexlabs:anythingllm:*:*:*:*:*:*:*:*\",\"versionEndExcluding\":\"1.13.0\",\"matchCriteriaId\":\"7D3F2D07-39A6-41B7-A3F1-65E53AA98838\"}]}]}],\"references\":[{\"url\":\"https://github.com/Mintplex-Labs/anything-llm/commit/94ed62d320df1a06c229e4bc3ee09c2cb5111b33\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Patch\"]},{\"url\":\"https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Exploit\",\"Mitigation\",\"Vendor Advisory\"]},{\"url\":\"https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"tags\":[\"Exploit\",\"Mitigation\",\"Vendor Advisory\"]}]}}",
    "redhat_vex": {
      "current_release_date": "2026-05-30T08:13:05+00:00",
      "cve": "CVE-2026-48116",
      "id": "CVE-2026-48116",
      "initial_release_date": "2026-01-01T00:00:00+00:00",
      "product_status:known_not_affected": "1",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "AnythingLLM: RCE via ripgrep --pre argument injection in filesystem-search-files agent skill",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-48116.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-48116\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-05-30T02:22:29.307430Z\"}}}], \"references\": [{\"url\": \"https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-05-30T02:22:49.518Z\"}}], \"cna\": {\"title\": \"AnythingLLM: RCE via ripgrep --pre argument injection in filesystem-search-files agent skill\", \"source\": {\"advisory\": \"GHSA-6hrp-7mw6-8v59\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 7.5, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"HIGH\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"Mintplex-Labs\", \"product\": \"anything-llm\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 1.13.0\"}]}], \"references\": [{\"url\": \"https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59\", \"name\": \"https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/Mintplex-Labs/anything-llm/commit/94ed62d320df1a06c229e4bc3ee09c2cb5111b33\", \"name\": \"https://github.com/Mintplex-Labs/anything-llm/commit/94ed62d320df1a06c229e4bc3ee09c2cb5111b33\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. Prior to 1.13.0, the filesystem-search-files agent skill passes its LLM-controlled pattern parameter to ripgrep as a positional argument without a -- end-of-options separator. ripgrep parses any argument that starts with - as an option, so a pattern of --pre=/bin/sh turns ripgrep into a script executor: it runs /bin/sh \u003cfile\u003e for every file it walks. An attacker who can chat with an agent on a deployment with the filesystem plugin enabled (the default in the official Docker image) can use this, together with the sibling filesystem-write-text-file skill, to run arbitrary commands inside the AnythingLLM server container. This vulnerability is fixed in 1.13.0.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-77\", \"description\": \"CWE-77: Improper Neutralization of Special Elements used in a Command (\u0027Command Injection\u0027)\"}]}, {\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-88\", \"description\": \"CWE-88: Improper Neutralization of Argument Delimiters in a Command (\u0027Argument Injection\u0027)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-05-28T21:19:51.965Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-48116\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-05-30T02:22:53.743Z\", \"dateReserved\": \"2026-05-20T18:46:58.289Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-05-28T21:19:51.965Z\", \"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.