shop-low-performers

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external store catalogs and order histories, which represents an attack surface where malicious instructions could be embedded in product names or order metadata.
  • Ingestion points: Data enters the context via shop_list_products and shop_list_orders tool calls as specified in the Required Tool Workflow.
  • Boundary markers: The output template uses standard Markdown tables to display product information but does not implement specific delimiters or 'ignore embedded instructions' warnings for the data fields.
  • Capability inventory: The skill is limited to READ_ONLY operations, ranking data, and generating reports with back-office links. It does not possess write or delete capabilities.
  • Sanitization: There is no evidence of string sanitization or escaping for the data retrieved from the shop tools before it is interpolated into the final report.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 02:57 PM
Security Audit — agent-trust-hub — shop-low-performers