CVE-2026-30856
WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval.
Published Mar 7, 2026 · updated Jun 17, 2026 · tencent weknora
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.
Code
The project this record applies to. Exploit listings stay in References.
No public source repository is identified for this product.
Timeline
Detection, updates, and resolution for this record.
Mar 7, 2026 · NIST NVD
Detected
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 ov
Jun 17, 2026 · NIST NVD
Updated
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 ov
Affected
- cpe tencent/weknoraversion unspecified
Sources
- NIST NVDVulnerability recordCVE-2026-30856
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 a
nvd.nist.gov