api-mock-helper

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill suggests the use of standard API development tools, specifically the @stoplight/prism-cli and msw packages via npm, and the faker library in Python. These are well-known, reputable packages used extensively for local testing and development.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a multi-step workflow that prompts the user to transition to a separate skill (api-ratelimiting-helper). This creates a point where instructions from one skill are chained to another based on user interaction.
  • Ingestion points: User confirmation ("yes/no") and generated API definitions.
  • Boundary markers: Standard conversational boundaries.
  • Capability inventory: Generates static code and JSON templates; does not automate shell execution or persistent file system modifications.
  • Sanitization: Not applicable as the generated content is presented to the user for implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 06:25 PM