google-search
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The script 'scripts/search.py' makes network requests to 'googleapis.com' to fetch search results from Google's official Custom Search API.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted data from the web. Ingestion points: Search results returned by the Google API in 'scripts/search.py'. Boundary markers: Absent; results are printed as raw JSON. Capability inventory: The script performs network reads but lacks dangerous capabilities such as file-system writes, subprocess execution, or dynamic code evaluation. Sanitization: No filtering or escaping is applied to the retrieved search snippets or metadata before they are returned to the agent context.
Audit Metadata