iran-downloads
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions advise installing an external package
iran-downloads-mcpusing theuvxtool to enable the Model Context Protocol (MCP) server. This package is the implementation of the tools listed in the skill. - [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes metadata from external websites (Soft98, P30Download, Downloadly, VGDL), creating a potential surface for instructions embedded in that data to influence agent behavior.
- Ingestion points: External data enters the context via the
dl_search,dl_latest, anddl_itemtools defined inSKILL.md. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are present in the skill instructions.
- Capability inventory: The skill facilitates the retrieval of titles, summaries, and descriptions from external web sources.
- Sanitization: There is no evidence of sanitization or content validation for the data retrieved from the source sites.
Audit Metadata