google-search-api

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the langchain-scavio package, which is a vendor-managed library for LangChain integration.
  • [COMMAND_EXECUTION]: The documentation includes commands for package installation using pip and environment variable configuration using export.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external content from Google search results, such as snippets and AI overviews, which can contain malicious instructions.
  • Ingestion points: Data is ingested via the search result fields (e.g., organic_results, ai_overview) returned by the api.scavio.dev endpoint.
  • Boundary markers: The skill instructs the agent to cite sources but does not define clear delimiters or protective instructions for the search data.
  • Capability inventory: The skill performs network requests to the vendor's API to fetch search data.
  • Sanitization: No filtering or sanitization of search result content is mentioned before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:23 PM
Security Audit — agent-trust-hub — google-search-api