popout-talking-head-video

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the hyperframes CLI tool via npx to perform background removal and automated verification snapshots. These operations are restricted to local assets within the project directory.
  • [EXTERNAL_DOWNLOADS]: Fetches the hyperframes package from the public npm registry. This is an expected dependency for the skill's video processing functionality.
  • [DATA_EXFILTRATION]: Reads from and writes to the local assets/ directory. No external network exfiltration or access to sensitive system credentials was observed.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external media files (presenter.mp4) which represents a theoretical surface for indirect injection.
  • Ingestion points: presenter.mp4 source file.
  • Boundary markers: None present for media content.
  • Capability inventory: Subprocess execution (npx hyperframes), local file write operations.
  • Sanitization: No sanitization or validation of the media source content was identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 11:15 AM