muapi-award-ceremony-video

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's functionality is strictly scoped to collecting user-provided images and text to generate creative video content via a specialized API.
  • [COMMAND_EXECUTION]: Instructions involve using a CLI tool (muapi) and curl to interact with the service API. These operations are transparent and directly related to the skill's primary function.
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to communicate with the api.muapi.ai domain. This is the legitimate backend infrastructure for the Muapi service used by the skill.
  • [PROMPT_INJECTION]: While the winner_name input is interpolated into the generation prompt, the skill includes a manual confirmation step. The data flows into a creative video generation model, posing no risk of system-level privilege escalation or safety guideline bypass.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 05:42 PM
Security Audit — agent-trust-hub — muapi-award-ceremony-video