Skip to content
Heist/ feed
Back to feed
Medium

WeKnora: Tool Execution Hijacking via Ambigous Naming Convention In MCP client and Indirect Prompt Injection

Type: advisorySources: OSV

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.

Products
Not specified
Affected versions
Not specified
Fixed versions
Not specified
CVEs
CVE-2026-30856
Confirmed fixed CVEs
Not specified
Updated in this feed
3 Nov 2026, 09:45 UTC · Revision 1

Source evidence

WeKnora: Tool Execution Hijacking via Ambigous Naming Convention In MCP client and Indirect Prompt Injection

core-osv · Original source

Published 7 Mar 2026, 16:32 UTC

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.

osv:CVE-2026-30856
Complete source record
{
  "id": "5fbbdb6c421374a0acf3fd3e9c12a6879336805c36764fba33b49af9d6bbd3eb",
  "url": "https://osv.dev/vulnerability/CVE-2026-30856",
  "method": "structured",
  "payload": {
    "kind": "advisory",
    "title": "WeKnora: Tool Execution Hijacking via Ambigous Naming Convention In MCP client and Indirect Prompt Injection",
    "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.",
    "evidence": "osv:CVE-2026-30856",
    "products": [],
    "severity": "medium",
    "structured": {
      "id": "CVE-2026-30856",
      "aliases": [
        "CVE-2026-30856",
        "GHSA-67q9-58vj-32qx",
        "GO-2026-4638"
      ],
      "metrics": [
        {
          "type": "CVSS_V3",
          "score": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:L/A:L"
        }
      ],
      "affected": [
        {
          "ranges": [
            {
              "repo": "https://github.com/tencent/weknora",
              "type": "GIT",
              "events": [
                {
                  "introduced": "0"
                },
                {
                  "fixed": "2979f9764af4a6ae4e226be084a4fa91ed5c8249"
                }
              ],
              "database_specific": {
                "extracted_events": [
                  {
                    "range": [
                      {
                        "introduced": "0"
                      },
                      {
                        "fixed": "0.3.0"
                      }
                    ],
                    "source": "AFFECTED_FIELD",
                    "strategy": "StringRangeExpression"
                  },
                  {
                    "cpe": "cpe:2.3:a:tencent:weknora:*:*:*:*:*:*:*:*",
                    "range": [
                      {
                        "introduced": "0"
                      },
                      {
                        "fixed": "0.3.0"
                      }
                    ],
                    "source": "CPE_RANGE"
                  }
                ]
              }
            }
          ],
          "versions": [
            "v0.2.14",
            "v0.2.13",
            "v0.2.12",
            "v0.2.11",
            "v0.2.10",
            "v0.2.9",
            "v0.2.8",
            "v0.2.7",
            "v0.2.6",
            "v0.2.5",
            "v0.2.4",
            "v0.2.3",
            "v0.2.2",
            "v0.2.1",
            "v0.2.0",
            "v0.1.6",
            "v0.1.5",
            "v0.1.3",
            "v0.1.2",
            "v0.1.1",
            "v0.1.0"
          ],
          "database_specific": {
            "source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-30856.json"
          }
        }
      ],
      "modified": "2026-10-28T02:30:27.870167238Z",
      "provider": "osv",
      "references": [
        "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/30xxx/CVE-2026-30856.json",
        "https://github.com/Tencent/WeKnora/security/advisories/GHSA-67q9-58vj-32qx",
        "https://nvd.nist.gov/vuln/detail/CVE-2026-30856"
      ],
      "provider_metadata": {
        "cwe_ids": [
          "CWE-706"
        ],
        "cna_assigner": "GitHub_M",
        "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/30xxx/CVE-2026-30856.json"
      }
    },
    "related_cves": [
      {
        "value": "CVE-2026-30856",
        "evidence": "/id"
      }
    ],
    "security_relevant": true,
    "severity_evidence": "/severity/0/score"
  },
  "source_id": "core-osv",
  "document_id": 494298,
  "published_at": "2026-03-07T16:32:44.566+00:00"
}