claude-video-edit
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the Bash tool to execute FFmpeg and other CLI commands. While the instructions use quotes for variables like "$INPUT", there is a residual risk of command injection if the agent fails to sanitize user-provided filenames that might contain shell metacharacters or command substitutions.- [INDIRECT_PROMPT_INJECTION]: The skill operates on external media and metadata files. If the agent reads and processes output from tools like ffprobe or scenedetect which extract data from these untrusted files, there is a risk of indirect prompt injection if the extracted data contains malicious instructions.
- Ingestion points: External media files (video, image), LUT files (.cube), and font files.
- Boundary markers: None. The instructions do not specify how to handle or delimit data extracted from media files.
- Capability inventory: The skill utilizes Bash, Read, and Write tools to perform complex file operations and system commands.
- Sanitization: No explicit sanitization or validation steps are defined for handling external file content or tool outputs.
Audit Metadata