video-reframe
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill operates by invoking a local Python script (skills/shared/scripts/reframe.py) through shell commands. While this is the intended functionality for video processing, it involves direct interaction with the system shell.- [INDIRECT_PROMPT_INJECTION]: The skill instructions define shell command templates that interpolate user-provided data, such as video file paths and project names, into the command line. This pattern presents an attack surface where maliciously crafted file names could lead to command injection.
- Ingestion points: Video file path (<视频>) and output folder name (主题名).
- Boundary markers: None present in the command templates to prevent command injection.
- Capability inventory: Execution of system commands via the Python interpreter.
- Sanitization: No evidence of input validation or escaping for the user-provided strings.
Audit Metadata