google-search
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from web search results. It includes specific safety instructions to treat all search snippets and linked pages as untrusted source material, and explicitly warns against following instructions contained within that content or leaking API credentials to external URLs.
- [CREDENTIALS_UNSAFE]: The skill follows secure practices by instructing users to store the API key in environment variables rather than hardcoding it in prompts or code.
- [EXTERNAL_DOWNLOADS]: The skill references standard installation procedures for related tools and libraries within the vendor's ecosystem.
Audit Metadata