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-scaviopackage, which is a vendor-managed library for LangChain integration. - [COMMAND_EXECUTION]: The documentation includes commands for package installation using
pipand environment variable configuration usingexport. - [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 theapi.scavio.devendpoint. - 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