claude-video-promo
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches video and audio assets from well-known stock media providers Pixabay and Pexels during the video creation process.
- [COMMAND_EXECUTION]: Executes bundled Python scripts for media processing and utilizes
npx remotionfor video composition and rendering. - [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by processing user-defined text for video overlays and voiceovers.
- Ingestion points: Headlines, subtexts, and voiceover text provided in user requests or YAML configuration files.
- Boundary markers: No explicit delimiters or boundary markers are defined in the provided instructions.
- Capability inventory: Execution of shell commands via the Bash tool for script orchestration; file write access for generated configurations and media assets.
- Sanitization: Sanitization or escaping of external content before interpolation into scripts or configurations is not explicitly detailed.
Audit Metadata