iran-apps
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions include the installation of an external package,
iran-apps-mcp, using theuvxtool to provide the necessary tools. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process data from external sources (Cafe Bazaar and Myket), which may contain untrusted content such as app descriptions.
- Ingestion points: Metadata retrieval tools defined in
SKILL.md(ap_search,ap_app,ap_compare,ap_top,ap_similar). - Boundary markers: Absent; there are no instructions to delimit or ignore potential commands within the fetched app metadata.
- Capability inventory: The provided tools are primarily read-only for metadata and search results.
- Sanitization: No evidence of sanitization, filtering, or escaping of the external app data is provided in the skill instructions.
Audit Metadata