create-imessage-mockup

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the Chromium browser via the npx playwright install chromium command. This is a standard and expected installation step for the Playwright library, which is a well-known tool for browser automation.
  • [COMMAND_EXECUTION]: The script uses execSync to install browser binaries. This command is hardcoded and does not include user-controlled inputs, minimizing the risk of command injection.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate mockups, representing a potential surface for indirect prompt injection. However, it incorporates sanitization to mitigate this risk.
  • Ingestion points: The text field within the message objects of the input JSON file.
  • Boundary markers: A strict JSON schema is provided in the documentation to guide the agent in generating valid data.
  • Capability inventory: The skill is capable of local file system writes and headless browser execution via Playwright.
  • Sanitization: The escapeHTML function in generate.js escapes special characters before they are interpolated into the HTML template.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill operates entirely on local data and generates local output files. No hardcoded credentials, sensitive file access, or network exfiltration patterns were observed in the code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 04:39 PM
Security Audit — agent-trust-hub — create-imessage-mockup