serpapi-local-dev-loop
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions prioritize security by requiring the sanitization of fixtures, the removal of API keys from offline environments, and the rotation of keys if exposure is detected in history.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for handling untrusted external search results, which represents a potential indirect prompt injection surface.
- Ingestion points: Data is ingested via
WebFetchand local fixture files. - Boundary markers: The instructions call for a 'fixture-backed fake' client and an explicit live-recording boundary.
- Capability inventory: The skill utilizes
Bash(python3:*),Bash(npm:*),Write, andEdittools. - Sanitization: Step 3 explicitly mandates the removal of key-bearing URLs, raw HTML links, and account identifiers to prevent malicious payloads or sensitive data from entering the development loop.
- [EXTERNAL_DOWNLOADS]: The skill references the official SerpAPI Python client repository and documentation. These are well-known, trusted resources for the SerpAPI service.
Audit Metadata