google-image-api-skill
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes third-party data from Google Image search results, which could potentially contain malicious instructions intended to influence the agent's subsequent actions.
- Ingestion points: External metadata (titles, source names, and snippets) are fetched via
scripts/google_image_api.pythrough the BrowserAct API. - Boundary markers: Not present. The script output is printed directly to the agent's context without delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill has network access to the vendor's API and writes results to stdout for the agent to read.
- Sanitization: No specific filtering or sanitization is applied to the retrieved text fields before they are presented to the agent.
Audit Metadata