pricing-plans

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the @kelviq/mcp-server Node.js package for setup. This is a legitimate resource originating from the skill author ('kelviq').
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its data processing capabilities.
  • Ingestion points: External data enters the agent context via the kelviq:docs_read, kelviq:plan_retrieve, and kelviq:offering_get_product tools.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the documentation fetching flow.
  • Capability inventory: The skill can create, update, and publish pricing models, features, and entitlements across a product catalog.
  • Sanitization: There is no mention of sanitization or schema validation for the data retrieved from the documentation or API endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 06:17 AM
Security Audit — agent-trust-hub — pricing-plans