aso
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs its stated function of auditing mobile app listings using standard web fetching and visual analysis tools.
- [DATA_EXPOSURE]: The skill checks for a local context file (
product-marketing.md) to inform its audit. This is a legitimate use of local project context to avoid redundant questioning and provide more accurate analysis. - [PROMPT_INJECTION]: The instructions do not contain any attempts to override agent behavior, bypass safety protocols, or extract system prompts.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns, package installations, or dynamic code execution were found.
- [EXTERNAL_DOWNLOADS]: The skill fetches data from well-known domains (apps.apple.com, play.google.com) which are necessary for its audit functionality. These are considered safe sources.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from public app store listings, including user-generated reviews and descriptions. While this is a potential attack surface, the risk is negligible as the skill only performs text analysis and report generation without dangerous execution capabilities.
Audit Metadata