tw-ecom-dtc-shopline

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill's methodology involves processing untrusted third-party data which introduces a surface for indirect prompt injection attacks.
  • Ingestion points: The skill retrieves user-controlled strings via tools like get_customer_profile, list_conversations, and list_product_reviews as documented in references/tool-catalog.md.
  • Boundary markers: Neither SKILL.md nor the sample scenarios implement delimiters or instructions to treat ingested strings as untrusted data.
  • Capability inventory: The skill has access to 68 write-capable tools (prefixed with [WRITE]) that can modify production state across orders, customers, and promotions.
  • Sanitization: There is no guidance for validating or escaping external content before it is interpolated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:09 PM
Security Audit — agent-trust-hub — tw-ecom-dtc-shopline