motion-effects

Warn

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use npx to download and execute the hyperframes package from the NPM registry. This introduces a dependency on an external package that is not part of a pre-verified trusted organization list.
  • [COMMAND_EXECUTION]: The skill includes a shell command (npx hyperframes remove-background take.mp4 -o person.webm --quality best) in SKILL.md to perform background removal on video files.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process user-provided video, audio, and social media content to generate complex motion graphics, creating a surface for indirect attacks.
  • Ingestion points: User-provided video files (take.mp4), audio waveform data, and social media post content (text and images) mentioned in SKILL.md and references/effects.md.
  • Boundary markers: The skill lacks explicit boundary markers or instructions for the agent to ignore any embedded commands within the processed data.
  • Capability inventory: The skill utilizes shell command execution (npx) for video processing tasks as seen in SKILL.md.
  • Sanitization: There is no evidence of sanitization or validation of the media content or its metadata before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 18, 2026, 05:06 PM