video-storytelling

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [SAFE]: The skill defines a structured workflow for video storytelling using local Python and Node.js scripts for generation and quality assurance. All external tools mentioned, such as ffmpeg and hyperframes, are standard in the described creative field.\n- [INDIRECT_PROMPT_INJECTION]: The skill involves processing word-level transcripts for timing visuals.\n
  • Ingestion points: Word-level transcripts (referenced in SKILL.md, Step 1 of Order of Work).\n
  • Boundary markers: None explicitly mentioned for transcript content.\n
  • Capability inventory: Execution of Python build scripts, Node.js QA scripts, and system tools like ffmpeg.\n
  • Sanitization: None mentioned, as the data is used for deterministic timing synchronization rather than text processing or command interpolation.\n- [DYNAMIC_EXECUTION]: The workflow involves generating HTML, SVG, and JavaScript assets through Python build scripts. This dynamic generation is a core, legitimate component of the storytelling system described and does not incorporate untrusted external input into the code generation process.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 01:50 PM