skills/vasanth19/skills/c-web-capture/Gen Agent Trust Hub

c-web-capture

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local JavaScript scripts (_scripts/capture-website-broll.mjs, _scripts/discover-broll-urls.mjs, _scripts/capture-playwright-auth-save.mjs) using Node.js and invokes system binaries like ffmpeg and ffprobe via the Bash tool to process and verify video output.
  • [DATA_EXPOSURE]: The instructions describe saving browser authentication states to a local file ($HOME/.playwright/example-auth.json). This is a standard mechanism for Playwright to persist session data for automated navigation on authenticated pages.
  • [PROMPT_INJECTION]: The discover-broll-urls.mjs script ingests content from external websites, creating a surface for potential indirect prompt injection.
  • Ingestion points: External web content enters the agent's context through the domain analysis script _scripts/discover-broll-urls.mjs.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded content were found in the provided markdown instructions.
  • Capability inventory: The skill is configured with Bash access, allowing it to execute scripts and manipulate the file system.
  • Sanitization: There is no evidence in the SKILL.md of sanitization or filtering of the content retrieved from external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 12:57 AM