places
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation instructs the user to install a CLI tool from a third-party Homebrew repository:
steipete/tap/goplaces. - [INDIRECT_PROMPT_INJECTION]: The skill processes user reviews fetched from the Google Places API, which is a source of untrusted external content.
- Ingestion points: Review snippets and full reviews are ingested into the agent's context as described in
SKILL.mdvia thegoplaces reviewscommand. - Boundary markers: There are no instructions defining delimiters or safety warnings for the agent when handling these external text inputs.
- Capability inventory: The skill is configured with
Bash,Read, andWritecapabilities, which could be leveraged if an injection is successful. - Sanitization: The instructions do not specify any validation, filtering, or escaping of the review content before it is processed by the model.
- [COMMAND_EXECUTION]: The skill relies on the
Bashtool to execute thegoplacesCLI for all operations, including searching, retrieving place details, and listing reviews.
Audit Metadata