muapi-freeze-effect-video

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the muapi command-line tool and curl to interact with the vendor's video generation API (api.muapi.ai). These operations are consistent with the skill's primary purpose of generating video content.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text for scene, freeze_moment, and closing_line, which are then interpolated into a complex generation prompt for a video model. While this creates a surface for indirect prompt injection, the impact is limited to the generated video output and is considered a low-risk design for this specific creative application.
  • Ingestion points: User inputs are gathered via the scene, freeze_moment, and closing_line parameters defined in SKILL.md.
  • Boundary markers: The variables are placed directly within a markdown code block representing the prompt without specific escaping or delimiters.
  • Capability inventory: The agent uses the muapi CLI or curl to send the final prompt to an external API.
  • Sanitization: No specific sanitization or validation of the user text is performed before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 11:14 PM