aso
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from App Store and Google Play listings, including description text and user reviews. This serves as a surface for indirect prompt injection if attackers embed malicious instructions in those fields. The skill mitigates this by explicitly instructing the agent to ignore instructions embedded in listing copy or reviews. Ingestion points include listing pages and screenshots. Capability inventory is limited to analysis and report generation. Boundary markers are present in the 'Before Auditing' section of SKILL.md. Sanitization is handled through instruction-based filtering.
Audit Metadata