Skills
skills/40rty-ai/shopify-admin-skills/collection-membership-audit/Gen Agent Trust Hub

collection-membership-audit

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted product and collection data from the Shopify API, creating a surface for indirect prompt injection where malicious instructions in product titles could influence agent behavior.
  • Ingestion points: products and collections GraphQL query results in SKILL.md.
  • Boundary markers: Absent; there are no instructions to delimit or ignore instructions within the retrieved data.
  • Capability inventory: Uses the shopify-admin toolkit for API access and has the ability to write CSV files to the local file system.
  • Sanitization: No explicit sanitization or escaping of external content is performed before processing or output generation.
  • [SAFE]: The skill specifies read-only GraphQL operations and requests minimal API scopes (read_products). No unauthorized network operations, hardcoded credentials, or persistence mechanisms were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 04:14 AM