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 Bash tool 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, and bash scripts/preflight.sh within SKILL.md.
  • It also utilizes system diagnostic tools like nvidia-smi for VRAM management and ffprobe for 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 $INPUT video file variable used in ffprobe and the enhancement scripts in SKILL.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, and Write tools, 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
Risk Level
SAFE
Analyzed
Sep 18, 2026, 02:31 PM
Security Audit — agent-trust-hub — claude-video-enhance