video-captioner

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill possesses an attack surface for instructions embedded in external data files.
  • Ingestion points: Data enters the agent context through the import_srt and import_captions_json methods described in SKILL.md.
  • Boundary markers: No delimiters or instructions to ignore embedded commands are present in the documentation or code samples.
  • Capability inventory: The skill leverages moviepy and pillow (defined in scripts/requirements.txt), which provide extensive video and image manipulation capabilities, often involving internal subprocess calls to system tools like ffmpeg.
  • Sanitization: There is no mention of text sanitization or filtering for the content loaded from external files before it is processed or rendered.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:42 PM