commercetools-connect

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes documentation content fetched from the official vendor API at runtime.
  • Ingestion points: scripts/docs-search.mjs retrieves results from https://docs.commercetools.com/apis/rest/tools/documentation-search.
  • Boundary markers: Not present; the content is provided as direct context to the agent.
  • Capability inventory: The agent can execute scripts for schema inspection and generate integration code.
  • Sanitization: The retrieval script filters out certain content types to minimize injection risk.
  • [EXTERNAL_DOWNLOADS]: The skill uses Node.js scripts to fetch live documentation and API metadata from vendor-controlled domains.
  • Evidence: scripts/docs-search.mjs, scripts/graphql-schemata.mjs, and scripts/openApi-schemata.mjs perform HTTP GET requests to docs.commercetools.com.
  • Context: These operations are part of the core functionality to provide up-to-date grounding for the AI agent and are conducted against trusted vendor infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 03:30 PM
Security Audit — agent-trust-hub — commercetools-connect