aso
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data fetched from external App Store and Google Play listing pages, creating a potential surface for indirect prompt injection.
- Ingestion points: Listing metadata, descriptions, and reviews are retrieved via WebFetch and screenshot tools as described in SKILL.md (Phase 1).
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be embedded in the fetched content (e.g., within an app description).
- Capability inventory: The skill is primarily analytical; it utilizes WebFetch, search, and screenshot tools but does not demonstrate capabilities for file system modification, persistence, or privilege escalation.
- Sanitization: The instructions do not specify any sanitization, filtering, or validation of the external content before it is processed by the agent.
Audit Metadata