skills/apify/openclaw/video-frames/Gen Agent Trust Hub

video-frames

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/frame.sh executes the ffmpeg command-line utility to perform video processing. This involves reading input video files, applying filters, and writing output images to the file system.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external video files and accepts user-controlled parameters that are passed into the ffmpeg command-line interface.
  • Ingestion points: File paths and extraction parameters (time and index) are passed as arguments to scripts/frame.sh (e.g., in SKILL.md usage examples).
  • Boundary markers: The skill does not implement specific boundary markers or "ignore previous instructions" warnings when handling potentially untrusted file paths provided by an agent's context.
  • Capability inventory: The skill possesses the capability to create directories via mkdir -p, read arbitrary files accessible to the user via ffmpeg, and write files to specified output paths.
  • Sanitization: The script includes basic validation to ensure the input file exists ([[ ! -f "$in" ]]) and uses shell quoting for variables, but it lacks strict type or format validation for the --index and --time parameters, potentially allowing for tool-specific argument injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 05:51 PM