aso
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (app listings and reviews) from third-party sources, which constitutes a potential attack surface. However, the skill incorporates robust safety guidelines to mitigate this risk.\n
- Ingestion points: The skill uses a web-fetching tool to ingest content from App Store and Google Play URLs as defined in SKILL.md.\n
- Boundary markers: Present. The skill explicitly instructs the agent to treat all fetched data as untrusted and specifically warns against following instructions embedded in the app copy or reviews.\n
- Capability inventory: The agent's capabilities are focused on analysis, scoring, and report generation; no dangerous execution or write capabilities are invoked.\n
- Sanitization: Logic-level sanitization is provided via the instruction to ignore any commands found within the external metadata.\n- [SAFE]: No other malicious patterns, such as hardcoded credentials, obfuscation, persistence mechanisms, or unauthorized privilege escalation, were detected. The use of external resources is limited to well-known, trusted domains for the legitimate purpose of retrieving public app information.
Audit Metadata