aso
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a standard indirect prompt injection surface as it ingests and processes untrusted external content (app descriptions and user reviews) from the App Store and Google Play.
- Ingestion points: Public app listing data retrieved via WebFetch and visual data from screenshots.
- Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions found within the scraped listing content.
- Capability inventory: The skill primarily performs data analysis and report generation based on the retrieved content.
- Sanitization: No specific sanitization or filtering logic is provided for the external text before it is processed by the agent.
- [DATA_EXFILTRATION]: The skill performs network operations to fetch data from well-known, trusted domains (apps.apple.com and play.google.com). It does not attempt to access sensitive local files or transmit private user data to unauthorized third parties.
Audit Metadata