google-maps-reviews
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
curlandpython3to interact with an external API. The execution is handled via shell scripts and Python heredocs with proper argument escaping to prevent command injection. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external source (Google Maps reviews) which is then returned to the agent context.
- Ingestion points: API responses retrieved in
scripts/get_google_maps_reviews.share passed back to the agent. - Boundary markers: Absent; the data is returned as raw JSON without explicit encapsulation or warnings to the LLM.
- Capability inventory: The skill has the ability to perform network requests (
curl) and write to the local file system (via the--outputflag). - Sanitization: Absent; the skill performs JSON structural validation but does not filter or sanitize the content of the reviews themselves.
- [CREDENTIALS_SAFE]: Authentication is managed through the
FREVANA_TOKENenvironment variable or an interactive prompt, following standard secure practices for API token management.
Audit Metadata