to-video

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes multiple external files (e.g., STORYBOARD.md, BRIEF.md, NARRATION.md) which serve as ingestion points for untrusted data.
  • Ingestion points: SKILL.md specifies reading BEATS.md, NARRATION.md, SCENES.md, STORYBOARD.md, BRIEF.md, and content artifacts from the project directory.
  • Boundary markers: The instructions do not specify the use of delimiters or "ignore embedded instructions" warnings when processing the contents of these artifacts.
  • Capability inventory: The skill utilizes the record-terminal sub-skill (involving shell and CLI operations) and various internal routes like /hyperframes and /listenhub-tts for production.
  • Sanitization: No explicit sanitization, escaping, or validation of the input file content is described before the data is interpolated into the production workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 08:15 AM