claude-video-audio

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute FFmpeg for audio processing and ffprobe for stream analysis.
  • [COMMAND_EXECUTION]: It executes a local script at scripts/preflight.sh to prepare files for processing.
  • [COMMAND_EXECUTION]: The skill invokes the auto-editor command-line utility for silence detection and removal.
  • [COMMAND_EXECUTION]: The processing of external media files presents a potential surface for indirect prompt injection. Ingestion points: User-provided media files via the $INPUT variable. Capability inventory: Execution of shell commands and FFmpeg filters. Boundary markers: No delimiters are used to isolate metadata. Sanitization: Uses shell variable quoting.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 02:55 PM
Security Audit — agent-trust-hub — claude-video-audio