pricing-as-code

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @kelviq/cli package globally via npm. This is a vendor-owned package provided by the skill author for managing pricing catalogs.
  • [COMMAND_EXECUTION]: Instructions guide the agent to execute kelviq CLI commands such as login, pull, push, and promote. The skill explicitly mandates that agents perform dry runs and present diffs to the human user for approval before applying any changes with --yes or non-dry-run flags.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined TypeScript configuration files and CLI-generated diff output, which could technically contain untrusted content if the local environment is compromised.
  • Ingestion points: Local kelviq.config.ts files and CLI stdout during dry runs (documented in SKILL.md).
  • Boundary markers: The instructions include a safety protocol requiring a human to review the dry-run diff before the agent can execute an apply command.
  • Capability inventory: CLI tool execution for environment synchronization (pull, push, promote).
  • Sanitization: The skill documentation notes that the backend server performs validation on all pushed configuration values.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 12:10 PM