CVE-2026-30856
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.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.26%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 3.1
- 7.6 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:L/A:L
- EPSS
- 0.26% probability · 17th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-706
- Affected
- tencent/weknora
- Source
- security-advisories@github.com
References
- https://github.com/Tencent/WeKnora/security/advisories/GHSA-67q9-58vj-32qxExploit, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.