clip-stream

Pass

Audited by Gen Agent Trust Hub on Nov 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill extensively uses the child_process.spawn module to invoke external binaries such as ffmpeg, ffprobe, yt-dlp, and streamlink for video analysis, downloading, and cutting.
  • Evidence: The lib/process.mjs file provides run and runCapture wrappers used by scripts/cut-clips.mjs, scripts/find-moments.mjs, and scripts/watch-live.mjs to execute tasks on the host system.
  • [EXTERNAL_DOWNLOADS]: The skill downloads content from external URLs using yt-dlp and streamlink. Additionally, it recommends using npx hyperframes for transcription, which triggers a download and execution of code from the npm registry.
  • Evidence: SKILL.md and scripts/watch-live.mjs contain instructions and logic for recording remote video streams.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted user-generated content from Twitch chat and chat logs, which is used to score highlights.
  • Ingestion points: chat.json (read in find-moments.mjs) and live IRC chat from irc.chat.twitch.tv (read in watch-live.mjs).
  • Boundary markers: Not explicitly defined for the chat data, but the content is processed via algorithmic token matching rather than being directly interpolated into agent prompts.
  • Capability inventory: The skill can write files, execute subprocesses, and perform network operations.
  • Sanitization: The chatSignal function in lib/moments.mjs mitigates risk by tokenizing input and matching against a static whitelist of hype-related tokens (e.g., 'lol', 'pog'), which prevents the interpretation of chat text as instructions.
  • [DYNAMIC_EXECUTION]: The watch-live.mjs script manages its complex workflow by dynamically spawning node processes to run other scripts provided with the skill.
  • Evidence: scripts/watch-live.mjs spawns node find-moments.mjs and node cut-clips.mjs as subprocesses.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 21, 2026, 05:02 PM