muapi-fashion-try-on
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external image data, creating a potential surface for indirect prompt injection. Ingestion points: person_image and clothing_image parameters defined in SKILL.md. Boundary markers: None identified; the agent is instructed to use inputs directly without delimiters to isolate user-provided content. Capability inventory: The skill utilizes the muapi CLI and curl for network requests to api.muapi.ai. Sanitization: No input validation or filtering is performed on the provided image URLs or their content.
- [COMMAND_EXECUTION]: The skill utilizes command-line tools including the muapi CLI and curl to interact with the MuAPI backend API for image and video processing, which are the primary tools required for the skill's stated purpose.
Audit Metadata