genkit-index
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data via the
user-genkitMCP tools (search_genkit_docs,read_genkit_docs) to guide "build or audit tasks". This creates an attack surface where malicious instructions embedded in the documentation could influence the agent's behavior. - Ingestion points: Documentation retrieval via
search_genkit_docsandread_genkit_docsas specified inSKILL.md. - Boundary markers: The instructions lack delimiters or warnings to ignore potential instructions within the retrieved documentation.
- Capability inventory: The skill routes to other domain skills for implementation tasks, which typically require file system access or code execution capabilities to perform "build" operations.
- Sanitization: No validation or sanitization logic is defined for the content fetched from the MCP.
Audit Metadata