documentation-lookup
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data (documentation fetched via MCP) which could theoretically contain instructions intended to influence the agent's behavior.
- Ingestion points: External data enters the agent context through the
query-docstool output as described inSKILL.md. - Boundary markers: The skill instructions do not define specific delimiters or warnings for the agent to ignore instructions embedded within the fetched documentation content.
- Capability inventory: The agent is instructed to use the fetched documentation to generate technical answers and provide code examples for the user.
- Sanitization: While the skill correctly mandates redacting secrets from outgoing queries to the service, it does not specify sanitization or validation techniques for the incoming documentation content.
Audit Metadata