skills/adobe/skills/reskin/Gen Agent Trust Hub

reskin

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a suite of local Node.js scripts (capture-content.mjs, dom-equality.mjs, donor-probe.mjs, slot-coverage.mjs) to automate its workflow phases. It also suggests using python3 -m http.server for serving local static prototypes.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the playwright package via NPM. Playwright is a well-known and trusted tool for browser automation and site rendering.
  • [DATA_EXFILTRATION]: While the skill accesses external URLs to capture website content and metadata, this activity is essential to its primary function of site migration. Data is processed locally, and no unauthorized transmission to third-party domains was detected.
  • [REMOTE_CODE_EXECUTION]: The skill uses page.evaluate() within Playwright to execute normalization logic in a browser context. This code is sourced from local, user-defined normalization ledgers and is used to handle DOM cleaning and carousel de-duplication.
  • [SAFE]: The author 'adobe' is a trusted vendor. The skill follows security best practices, such as suggesting the use of .env files for secrets (if needed, though none are hardcoded here) and providing clear documentation for its programmatic operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 09:02 PM
Security Audit — agent-trust-hub — reskin