commercetools-integrations

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill uses scripts to fetch grounding context from official commercetools documentation endpoints. This represents a potential surface for indirect prompt injection if the source content were compromised, but is a standard and legitimate practice for vendor-authored tools provided the source is trusted.
  • Ingestion points: scripts/docs-search.mjs, scripts/graphql-schemata.mjs, and scripts/openApi-schemata.mjs fetch content from external URLs.
  • Boundary markers: Not explicitly used to isolate external content in the terminal output.
  • Capability inventory: The skill provides instructions for the agent to execute commercetools CLI commands, perform network requests, and run local node scripts.
  • Sanitization: Fetched content is output directly for agent processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:55 PM
Security Audit — agent-trust-hub — commercetools-integrations