CVE-2026-30856
Title: Tool name collision and indirect prompt injection
Proof Of Concept
No public PoC currently indexed for CVE-2026-30856.
Vulnerability Summary
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.
Impacted Vendors
Reference Links
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:L/A:L
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:L/A:L
Associated Attack Patterns (CAPEC)
Total: PatternsNo specific attack patterns mapped.
CVE-2026-30856 Exploits & PoCs (Proof Of Concept)
No public PoCs found in our database for this CVE.
Vulnerability data updated via NVD.
Vulnerability data updated via NVD.
Vulnerability data updated via NVD.
Vulnerability data updated via NVD.
Attack Vector Matrix
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:L/A:L
Affected Stack
No specific products linked.