muapi-freeze-effect-video

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted user data via the scene, freeze_moment, and closing_line inputs, which are interpolated directly into a complex multi-line prompt for video generation without delimiters or instructions to ignore embedded commands. This creates a surface for indirect prompt injection.
  • Ingestion points: SKILL.md input parameters.
  • Boundary markers: Absent.
  • Capability inventory: muapi CLI execution and network access via curl to api.muapi.ai.
  • Sanitization: No sanitization or validation is applied to user-supplied text before interpolation.
  • [COMMAND_EXECUTION]: The skill utilizes the muapi CLI tool and curl for its core functionality. These operations are within the expected scope of a video generation utility and follow standard authentication practices using environment variables.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with api.muapi.ai. As this is the official endpoint for the skill's vendor, the network operations are considered legitimate and safe within the context of the skill's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:04 PM
Security Audit — agent-trust-hub — muapi-freeze-effect-video