FKIE_CVE-2024-12704

Vulnerability from fkie_nvd - Published: 2025-03-20 10:15 - Updated: 2025-10-15 13:15
Severity ?
7.5 (High) - CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Summary
A vulnerability in the LangChainLLM class of the run-llama/llama_index repository, version v0.12.5, allows for a Denial of Service (DoS) attack. The stream_complete method executes the llm using a thread and retrieves the result via the get_response_gen method of the StreamingGeneratorCallbackHandler class. If the thread terminates abnormally before the _llm.predict is executed, there is no exception handling for this case, leading to an infinite loop in the get_response_gen function. This can be triggered by providing an input of an incorrect type, causing the thread to terminate and the process to continue running indefinitely.
References
security@huntr.devhttps://github.com/run-llama/llama_index/commit/d1ecfb77578d089cbe66728f18f635c09aa32a05Patch
security@huntr.devhttps://huntr.com/bounties/a0b638fd-21c6-4ba7-b381-6ab98472a02aExploit, Third Party Advisory
Impacted products
Vendor Product Version
llamaindex llamaindex 0.12.5
To clipboard 

{
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:llamaindex:llamaindex:0.12.5:*:*:*:*:*:*:*",
              "matchCriteriaId": "D35A0A81-3555-4025-9D5B-FE7435EA5747",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "A vulnerability in the LangChainLLM class of the run-llama/llama_index repository, version v0.12.5, allows for a Denial of Service (DoS) attack. The stream_complete method executes the llm using a thread and retrieves the result via the get_response_gen method of the StreamingGeneratorCallbackHandler class. If the thread terminates abnormally before the _llm.predict is executed, there is no exception handling for this case, leading to an infinite loop in the get_response_gen function. This can be triggered by providing an input of an incorrect type, causing the thread to terminate and the process to continue running indefinitely."
    },
    {
      "lang": "es",
      "value": "Una vulnerabilidad en la clase LangChainLLM del repositorio run-llama/llama_index, versi\u00f3n v0.12.5, permite un ataque de denegaci\u00f3n de servicio (DoS). El m\u00e9todo stream_complete ejecuta el llm mediante un hilo y recupera el resultado mediante el m\u00e9todo get_response_gen de la clase StreamingGeneratorCallbackHandler. Si el hilo termina de forma an\u00f3mala antes de ejecutar _llm.predict, no se gestionan excepciones, lo que genera un bucle infinito en la funci\u00f3n get_response_gen. Esto puede activarse al proporcionar una entrada de un tipo incorrecto, lo que provoca la finalizaci\u00f3n del hilo y la ejecuci\u00f3n indefinida del proceso."
    }
  ],
  "id": "CVE-2024-12704",
  "lastModified": "2025-10-15T13:15:40.547",
  "metrics": {
    "cvssMetricV30": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 7.5,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "NONE",
          "integrityImpact": "NONE",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
          "version": "3.0"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 3.6,
        "source": "security@huntr.dev",
        "type": "Secondary"
      }
    ]
  },
  "published": "2025-03-20T10:15:29.383",
  "references": [
    {
      "source": "security@huntr.dev",
      "tags": [
        "Patch"
      ],
      "url": "https://github.com/run-llama/llama_index/commit/d1ecfb77578d089cbe66728f18f635c09aa32a05"
    },
    {
      "source": "security@huntr.dev",
      "tags": [
        "Exploit",
        "Third Party Advisory"
      ],
      "url": "https://huntr.com/bounties/a0b638fd-21c6-4ba7-b381-6ab98472a02a"
    }
  ],
  "sourceIdentifier": "security@huntr.dev",
  "vulnStatus": "Modified",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-835"
        }
      ],
      "source": "security@huntr.dev",
      "type": "Primary"
    }
  ]
}


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.