ecommerce-returns

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data sources which could potentially contain malicious instructions intended to influence agent behavior.\n
  • Ingestion points: The skill ingests return exports, sales volume data, and product type information provided by the user via MCP, CSV, or direct pasting (SKILL.md).\n
  • Boundary markers: While functional boundaries exist to distinguish coded reason fields from free-text, there are no explicit delimiters or instructions to ignore commands that may be embedded in data labels.\n
  • Capability inventory: The skill allows the agent to write context to .agents/product-context.md, perform web searches for industry benchmarks, and render visual artifacts (SKILL.md).\n
  • Sanitization: No explicit sanitization or filtering of input strings is performed before the data is processed or interpolated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 04:06 PM