muapi-freeze-effect-video

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text for 'scene', 'freeze_moment', and 'closing_line' which are interpolated directly into the complex prompt sent to the video generation tool.
  • Ingestion points: Variables are defined in the 'Inputs' section of SKILL.md and used in Phase A.
  • Boundary markers: No delimiters or safety instructions are used to separate user input from the rest of the generation prompt.
  • Capability inventory: The skill utilizes network operations via the 'muapi' CLI and 'curl' to interact with remote APIs.
  • Sanitization: There is no evidence of validation or filtering for the user-supplied text inputs.
  • [COMMAND_EXECUTION]: The skill instructions direct the executing agent to run shell commands including 'muapi auth configure' and 'curl' to interact with the vendor's API endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 07:17 AM