seenry-video
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Multiple scripts (
mix.py,render.mjs,film_check.py) executeffmpegandffprobeto handle media processing. These executions use list-based arguments, which is a secure practice that avoids shell injection vulnerabilities. - [DYNAMIC_EXECUTION]: The skill uses Playwright to render HTML templates into video frames. This involves executing JavaScript within a headless browser, which is the primary mechanism for the skill's film rendering functionality and is scoped to a local-only environment.
- [EXTERNAL_DOWNLOADS]: The
elevenlabs.pyscript makes network calls to the ElevenLabs API for sound generation. This is an integration with a well-known service, and the skill correctly manages the required API keys through environment variables rather than hardcoding them. - [INDIRECT_PROMPT_INJECTION]: The automated review process in
film_critic.mjsincorporates project-specific markdown files into an LLM prompt. This represents a typical use case for AI-assisted critique and is constrained by the script's internal logic and rubric.
Audit Metadata