video-clip-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the openclip tool from the author's official GitHub repository (github.com/linzzzzzz/openclip) during the setup phase.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute git for code retrieval, uv for dependency management, and python for running the core orchestration script.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, such as video transcripts and subtitles, which creates a potential surface for indirect prompt injection.
- Ingestion points: Transcripts and subtitles are retrieved from external video hosting platforms or local files (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested data.
- Capability inventory: The skill has the ability to read and write files in the local directory and execute ffmpeg for video manipulation (SKILL.md).
- Sanitization: No sanitization or validation of the transcript content is specified before it is analyzed by the language model.
Audit Metadata