aso
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a structured analysis framework for evaluating public mobile app listings. The logic is purely instructional, referencing static benchmark data and using standard web fetching tools to gather information. It does not perform any sensitive system operations, execute shell commands, or handle user credentials.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it ingests and processes untrusted text from external App Store and Google Play listing pages, such as descriptions and user reviews.
- Ingestion points: External app listing data is retrieved via WebFetch in Phase 1 of
SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' commands for the retrieved external text.
- Capability inventory: The skill's capabilities are restricted to generating a text-based audit report. There is no evidence of subprocess execution, file system writes, or network operations that could be exploited via injection.
- Sanitization: No explicit sanitization or filtering logic is present for the fetched listing content. Given the lack of sensitive capabilities, the indirect injection surface represents a negligible risk.
Audit Metadata