html-export

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes HTML files, which represent an untrusted data surface for the AI agent.
  • Ingestion points: Positional arguments provided as <input...> are processed by scripts/lib/to-png.cjs, scripts/lib/to-pdf.cjs, and scripts/lib/to-video.cjs.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when the agent is instructed to process or verify the exported content.
  • Capability inventory: The skill executes subprocesses (ffmpeg in scripts/lib/ffmpeg.cjs), performs file system writes (fs.writeFileSync in scripts/lib/result.cjs), and controls a browser environment via Playwright.
  • Sanitization: Input filenames are sanitized in scripts/lib/paths.cjs, but the content of the HTML is rendered without sanitization.
  • [DATA_EXFILTRATION]: The skill has a risk of data exposure through local file inclusion. As explicitly noted in the documentation, Chromium runs without an OS sandbox in this implementation, which allows a malicious HTML file to use elements like iframes to embed local files (e.g., SSH keys or credentials) into the generated PNG, PDF, or video files.
  • The skill provides an --offline flag which mitigates network-based exfiltration, but it does not prevent the exposure of local data into the exported files themselves.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 01:34 AM