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, andlist_product_reviewsas documented inreferences/tool-catalog.md. - Boundary markers: Neither
SKILL.mdnor 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