video-editor
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
ffmpegandffprobefor video processing. It implements defensive measures by instructing the agent to validate file paths for shell metacharacters and wrap them in single quotes. The provided Python scripts securely use list-based arguments forsubprocess.run, avoiding shell execution vulnerabilities.- [PROMPT_INJECTION]: The skill handles untrusted external data from SRT files and editing guides. It includes explicit instructions for the agent to ignore any embedded 'ignore previous instructions' or other injection attempts, which is a proactive defense against indirect prompt injection.- [EXTERNAL_DOWNLOADS]: Dependencies like FFmpeg are managed via standard system package managers (brew, apt, winget). No unverified remote code or scripts are downloaded or executed.
Audit Metadata