aso
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill is configured to read local marketing context files (e.g., product-marketing.md) if available to inform its audit. This file system access is restricted to specific filenames and serves a legitimate functional purpose.
- [EXTERNAL_DOWNLOADS]: The agent retrieves public app listing data and captures screenshots from apps.apple.com and play.google.com using browsing tools. These domains are well-known, official sources for the skill's intended purpose.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it ingests and processes untrusted text from external website listings.
- Ingestion points: Listing descriptions and metadata are fetched from external store URLs via WebFetch in Phase 1 of SKILL.md.
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are specified for the fetched content.
- Capability inventory: The skill utilizes web browsing, screenshot capture, and local file reading (marketing context).
- Sanitization: No explicit sanitization or filtering of the fetched external content is described.
- [NO_CODE]: The skill consists entirely of markdown instructions and reference data, with no included executable scripts or compiled binaries.
Audit Metadata