Vulnerability Details CVE-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 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.
Exploit prediction scoring system (EPSS) score
EPSS Score 0.0
EPSS Ranking 5.6%
CVSS Severity
CVSS v3 Score 5.9
Products affected by CVE-2026-30856
-
cpe:2.3:a:tencent:weknora:0.1.0
-
cpe:2.3:a:tencent:weknora:0.1.1
-
cpe:2.3:a:tencent:weknora:0.1.2
-
cpe:2.3:a:tencent:weknora:0.1.3
-
cpe:2.3:a:tencent:weknora:0.1.4
-
cpe:2.3:a:tencent:weknora:0.1.5
-
cpe:2.3:a:tencent:weknora:0.1.6
-
cpe:2.3:a:tencent:weknora:0.2.0
-
cpe:2.3:a:tencent:weknora:0.2.1
-
cpe:2.3:a:tencent:weknora:0.2.2
-
cpe:2.3:a:tencent:weknora:0.2.3
-
cpe:2.3:a:tencent:weknora:0.2.4
-
cpe:2.3:a:tencent:weknora:0.2.5
-
cpe:2.3:a:tencent:weknora:0.2.6
-
cpe:2.3:a:tencent:weknora:0.2.7
-
cpe:2.3:a:tencent:weknora:0.2.8
-
cpe:2.3:a:tencent:weknora:0.2.9