serpapi

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted search results from external websites via SerpAPI.
  • Ingestion points: Search results from engines like Google and Amazon returned to the agent via serp.py.
  • Boundary markers: None identified in the skill's instructions or examples.
  • Capability inventory: The skill retrieves and formats external search data for agent consumption.
  • Sanitization: Implementation details for sanitizing external content are unavailable as scripts/serp.py is missing.
  • [Missing Source Code] (INFO): The skill documentation references a Python script scripts/serp.py which is not included in the provided files. Safety of execution and network behavior cannot be fully audited.
  • [Network Operation] (LOW): The tool is designed to communicate with serpapi.com to perform its search functions. While this is a non-whitelisted domain, the behavior is consistent with the skill's stated purpose.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 09:04 PM