etsy-tony-full-gigab2b-assets

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests untrusted data from external GigaB2B product pages and API responses.
  • Ingestion points: Data is ingested through browser-based page reading (instructed in references/photo-job-workflow.md) and API calls to openapi.gigab2b.com in scripts/etsy-tony-full-gigab2b-assets.mjs.
  • Boundary markers: There are no explicit boundary markers or "ignore instructions" warnings in the handoff files generated for subsequent image generation tasks.
  • Capability inventory: The skill has the capability to execute local scripts and write files to the filesystem.
  • Sanitization: The cleanText function in the script performs basic sanitization by removing HTML tags, but does not sanitize potential natural language instructions embedded in product titles or descriptions.
  • [COMMAND_EXECUTION]: The skill utilizes an internal Node.js script (scripts/etsy-tony-full-gigab2b-assets.mjs) to automate data collection and file management.
  • [EXTERNAL_DOWNLOADS]: The script downloads product images and reference files from external URLs provided by the GigaB2B API. These downloads are performed to a local output directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 03:46 AM
Security Audit — agent-trust-hub — etsy-tony-full-gigab2b-assets