Skills
skills/samuraigpt/generative-media-skills/muapi-selfie-with-celebrities/Gen Agent Trust Hub

muapi-selfie-with-celebrities

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the muapi CLI tool to orchestrate image and video generation.
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to use curl to reach https://api.muapi.ai. This is a well-known service domain for the specific tooling described.
  • [PROMPT_INJECTION]: Potential surface for indirect prompt injection via the movie_name input.
  • Ingestion points: movie_name variable in SKILL.md.
  • Boundary markers: None.
  • Capability inventory: muapi CLI, curl network access to api.muapi.ai.
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:05 PM
Security Audit — agent-trust-hub — muapi-selfie-with-celebrities