add-captions-burn

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/make_klap_style_subs.py uses subprocess.run() to execute ffmpeg. This is a core functional requirement of the skill to perform the video 'burning' process. The command is constructed using a list of arguments (avoiding shell injection) and operates on local file paths provided by the user.
  • [REMOTE_CODE_EXECUTION]: No remote code execution or external downloads were detected. The scripts are entirely local and do not fetch external dependencies or executable payloads.
  • [DATA_EXFILTRATION]: No network activity or exfiltration patterns were identified. The skill processes local subtitle (ASS/JSON) and video (MP4) files.
  • [PROMPT_INJECTION]: The instructions in SKILL.md and the test files do not contain any patterns attempting to override agent behavior or safety guidelines.
  • [STATIC_ANALYSIS]: The heuristic flag regarding subprocess.run() in scripts/make_klap_style_subs.py was evaluated and found to be benign, as it is used correctly for local media processing without using shell=True on untrusted input.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 04:38 PM
Security Audit — agent-trust-hub — add-captions-burn