serpapi-install-auth
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements secure credential handling by directing the agent to store the SERPAPI_KEY in a server-side secret manager and explicitly warning against committing secrets to version control or printing them to logs.\n- [SAFE]: Package installations (serpapi for Python and Node.js) and documentation fetches target official and well-known SerpAPI resources on GitHub and the company's primary domain.\n- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface.\n
- Ingestion points: Documentation is fetched from GitHub and SerpAPI domains via WebFetch; API responses are processed by the client.\n
- Boundary markers: None identified in the instructions for the ingested data.\n
- Capability inventory: Uses Bash for installation and Write/Edit for configuration.\n
- Sanitization: No explicit sanitization or validation logic is defined for external documentation content. The risk is assessed as safe due to the trusted nature of the sources and the requirement for operator approval for sensitive actions.
Audit Metadata