muapi-award-ceremony-video

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the muapi CLI tool and curl to interact with the service at api.muapi.ai. This execution is restricted to the primary function of submitting video generation tasks.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data which is interpolated into prompts for video generation, presenting a potential injection surface.\n
  • Ingestion points: User inputs for winner_name, winner_image, and host_image defined in SKILL.md.\n
  • Boundary markers: Not present; the user name is directly inserted into the prompt string.\n
  • Capability inventory: Interaction with external APIs via muapi CLI and curl commands.\n
  • Sanitization: No sanitization or validation of the user-provided text is performed before prompt construction.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 07:17 AM