{"id":"CVE-2026-30856","aliases":["GHSA-67q9-58vj-32qx","GO-2026-4638"],"url":"https://o3.security/vulnerability/CVE-2026-30856","summary":"WeKnora: Tool Execution Hijacking via Ambigous Naming Convention In MCP client and Indirect Prompt Injection","details":"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.","published":"2026-03-07T16:32:44.566Z","modified":"2026-07-31T18:29:54.644465157Z","cvss":{"score":5.9,"severity":"MEDIUM","vector":"CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:L/A:L"},"epss":null,"cisaKev":null,"exploitsKnown":0,"affectedPackages":[{"ecosystem":"Go","name":"github.com/Tencent/WeKnora","fixedVersion":"0.3.0"}],"fix":null,"references":[{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/30xxx/CVE-2026-30856.json"},{"type":"ADVISORY","url":"https://github.com/Tencent/WeKnora/security/advisories/GHSA-67q9-58vj-32qx"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-30856"}],"provenance":{"sources":["OSV.dev","FIRST.org (EPSS)"],"lastVerified":"2026-07-31T18:29:54.644465157Z"}}