serpapi

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted search results from various external search engines, which represents a potential injection surface.\n
  • Ingestion points: The search results are fetched via the SerpAPI service in scripts/serp.py.\n
  • Boundary markers: The skill does not implement specific delimiters or warnings for the agent to ignore embedded instructions in the search results.\n
  • Capability inventory: The skill performs network read operations and local file reads (TOOLS.md).\n
  • Sanitization: Search results are parsed and returned to the agent without additional filtering or sanitization.\n- [EXTERNAL_DOWNLOADS]: Fetches search data from serpapi.com, which is a well-known search aggregation service.\n- [DATA_EXFILTRATION]: Accesses the TOOLS.md configuration file in the user's home directory or workspace to retrieve default location settings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:31 PM
Security Audit — agent-trust-hub — serpapi