google-images-search
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local system utilities, specifically
bash,curl, andpython3, to handle CLI arguments, perform network requests, and validate JSON output. These operations are limited to the skill's intended functionality. - [EXTERNAL_DOWNLOADS]: Communicates with
ai-factory.frevana.comto fetch image search results. This is a core feature and targets the vendor's own infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Google Image results. While this constitutes an attack surface where search results could theoretically contain instructions designed to influence the agent, the skill itself does not provide high-privilege capabilities that would enable an exploit at this stage.
- [CREDENTIALS_UNSAFE]: The script manages the
FREVANA_TOKENusing environment variables and optional command-line overrides. It correctly suggests using environment variables as a safe practice for secret management.
Audit Metadata