skills/adobe/skills/extract/Gen Agent Trust Hub

extract

Pass

Audited by Gen Agent Trust Hub on Oct 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is configured to download website assets, including favicons (scripts/crawl.mjs), images, and font files (SKILL.md Phase 2), from the target domains being crawled to populate the local stardust/current/assets/ directory.
  • [COMMAND_EXECUTION]: The setup procedure and operational phases involve running Node.js scripts (scripts/crawl.mjs, scripts/style-census.mjs, scripts/thumb.mjs) and potentially installing necessary NPM packages (playwright, pixelmatch, pngjs, cheerio) to facilitate website rendering and analysis.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it processes untrusted data from external websites.
  • Ingestion points: scripts/crawl.mjs (via sitemap XML parsing and HTML link extraction).
  • Boundary markers: Absent in the raw text extraction; however, the reference/brand-review-template.md for reports enforces structural boundaries by embedding only CSS and forbidding external JavaScript.
  • Capability inventory: scripts/crawl.mjs (network operations, file writes), scripts/style-census.mjs (network operations, file writes), and scripts/thumb.mjs (file writes).
  • Sanitization: scripts/crawl.mjs implements visibility filters and an interstitial/error heuristic to exclude transient DOM elements and common overlays from the captured content.
  • [DYNAMIC_EXECUTION]: The scripts/style-census.mjs script utilizes dynamic import() to load its live-session.mjs dependency from relative local paths, ensuring modularity while limiting loading to known internal script locations.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 10, 2026, 01:45 PM