claude-video-enhance
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute a suite of local processing scripts and system utilities. - Evidence includes calls to
python3 scripts/video_enhance.py,bash scripts/estimate_size.sh, andbash scripts/preflight.shwithinSKILL.md. - It also utilizes system diagnostic tools like
nvidia-smifor VRAM management andffprobefor media metadata extraction. - [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection via the processing of external video files.
- Ingestion points: The skill ingests untrusted data through the
$INPUTvideo file variable used inffprobeand the enhancement scripts inSKILL.md. - Boundary markers: No specific boundary markers or instructions to ignore embedded metadata are present in the prompt instructions.
- Capability inventory: The skill has access to
Bash,Read, andWritetools, allowing for command execution and file system operations. - Sanitization: No explicit sanitization or validation logic for the input file's metadata is defined in the skill instructions.
Audit Metadata