aso
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches content from the Apple App Store and Google Play Store using WebFetch to perform audits. This data is untrusted and can contain malicious prompts embedded by third-party app developers designed to override the agent's behavior or bias the audit results.
- Ingestion points: Untrusted data enters the agent's context during the 'Fetch the listing' step in
SKILL.md(Phase 1), where the agent extracts all available fields including descriptions and reviews. - Boundary markers: The skill does not provide any delimiters (e.g., XML tags or clear labels) or 'ignore embedded instructions' warnings to prevent the agent from executing commands found within the fetched text.
- Capability inventory: The skill uses WebFetch for network access and vision/screenshot tools for visual assessment.
- Sanitization: No sanitization or filtering is performed on the externally fetched text before it is analyzed by the LLM.
Audit Metadata