FKIE_CVE-2026-30856

Vulnerability from fkie_nvd - Published: 2026-03-07 17:15 - Updated: 2026-03-09 13:35
Severity ?
5.9 (Medium) - CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:L/A:L
Summary
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming convention in the MCP client (mcp_{service}_{tool}), an attacker can register a malicious tool that overwrites a legitimate one (e.g., tavily_extract). This enables the attacker to redirect LLM execution flow, exfiltrate system prompts, context, and potentially execute other tools with the user's privileges. This issue has been patched in version 0.3.0.
References
security-advisories@github.comhttps://github.com/Tencent/WeKnora/security/advisories/GHSA-67q9-58vj-32qx
Impacted products
Vendor Product Version
To clipboard 

{
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0,  a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming convention in the MCP client (mcp_{service}_{tool}), an attacker can register a malicious tool that overwrites a legitimate one (e.g., tavily_extract). This enables the attacker to redirect LLM execution flow, exfiltrate system prompts, context, and potentially execute other tools with the user\u0027s privileges. This issue has been patched in version 0.3.0."
    },
    {
      "lang": "es",
      "value": "WeKnora es un framework impulsado por LLM dise\u00f1ado para la comprensi\u00f3n profunda de documentos y la recuperaci\u00f3n sem\u00e1ntica. Antes de la versi\u00f3n 0.3.0, una vulnerabilidad que implica colisi\u00f3n de nombres de herramientas e inyecci\u00f3n indirecta de prompts permite a un servidor MCP remoto malicioso secuestrar la ejecuci\u00f3n de herramientas. Al explotar una convenci\u00f3n de nombres ambigua en el cliente MCP (mcp_{service}_{tool}), un atacante puede registrar una herramienta maliciosa que sobrescribe una leg\u00edtima (por ejemplo, tavily_extract). Esto permite al atacante redirigir el flujo de ejecuci\u00f3n del LLM, exfiltrar prompts del sistema, contexto y potencialmente ejecutar otras herramientas con los privilegios del usuario. Este problema ha sido parcheado en la versi\u00f3n 0.3.0."
    }
  ],
  "id": "CVE-2026-30856",
  "lastModified": "2026-03-09T13:35:07.393",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "HIGH",
          "attackVector": "NETWORK",
          "availabilityImpact": "LOW",
          "baseScore": 5.9,
          "baseSeverity": "MEDIUM",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "LOW",
          "privilegesRequired": "LOW",
          "scope": "UNCHANGED",
          "userInteraction": "REQUIRED",
          "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:L/A:L",
          "version": "3.1"
        },
        "exploitabilityScore": 1.2,
        "impactScore": 4.7,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ]
  },
  "published": "2026-03-07T17:15:53.210",
  "references": [
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/Tencent/WeKnora/security/advisories/GHSA-67q9-58vj-32qx"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Undergoing Analysis",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-706"
        }
      ],
      "source": "security-advisories@github.com",
      "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.