aso
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection due to its reliance on external, untrusted content processing.\n
- Ingestion points: The skill instructions in
SKILL.mddirect the agent to fetch listing data, including titles, descriptions, and user reviews, fromapps.apple.comandplay.google.comusing web-fetching and screenshot tools.\n - Boundary markers: The instructions do not provide explicit delimiters or "ignore previous instruction" warnings to the agent when processing the fetched listing data.\n
- Capability inventory: The skill utilizes web search and browser fetching tools. It does not have access to sensitive local file paths (such as credentials) or the ability to execute code or shell commands.\n
- Sanitization: The instructions do not define any validation, escaping, or filtering of the external content before it is used to generate the ASO audit report.
Audit Metadata