CVE-2026-30856
Description
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.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
github.com/Tencent/WeKnoraGo | < 0.3.0 | 0.3.0 |
Affected products
1Patches
0No patches discovered yet.
Vulnerability mechanics
AI mechanics synthesis has not run for this CVE yet.
References
6- github.com/Tencent/WeKnora/security/advisories/GHSA-67q9-58vj-32qxnvdExploitVendor AdvisoryWEB
- github.com/advisories/GHSA-67q9-58vj-32qxghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2026-30856ghsaADVISORY
- forum.cursor.com/t/mcp-tools-name-collision-causing-cross-service-tool-call-failures/70946ghsaWEB
- modelcontextprotocol-security.io/ttps/tool-poisoning/tool-name-conflictghsaWEB
- www.elastic.co/security-labs/mcp-tools-attack-defense-recommendationsghsaWEB
News mentions
0No linked articles in our index yet.