restaurant-reviews
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is data aggregation and sentiment analysis of public web content. It does not attempt to access sensitive local files, environment variables, or hardcoded credentials.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from the web (restaurant reviews).
- Ingestion points: WebSearch results from Google, Yelp, and TripAdvisor are read into the agent context in Step 2.
- Boundary markers: The instructions do not define delimiters or warnings to ignore instructions embedded within the review text.
- Capability inventory: The skill has file-writing capabilities to save the final report.
- Sanitization: There is no explicit sanitization or filtering of the retrieved review content before processing.
Audit Metadata