api-design
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and provides a step-by-step methodology for API resource modeling, consumer analysis, and specification generation. It does not contain any executable code, obfuscated content, or unauthorized network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided answers to design questions to generate file content (OpenAPI specs) and perform git commits.
- Ingestion points: User responses to the discovery questions in Phase 1 and endpoint definitions in Phase 2 are used to populate the OpenAPI template in Phase 3.
- Boundary markers: The skill implements several 'STOP' gates requiring explicit user approval before proceeding to design, generation, or saving phases, which mitigates the risk of the agent autonomously performing unintended actions based on malicious input.
- Capability inventory: The skill uses file-writing capabilities to save documentation to
docs/api/and utilizes git for committing these changes. These are standard operations for a documentation-oriented skill. - Sanitization: While explicit sanitization logic is not defined within the skill itself, the reliance on the agent's internal safety filters and the mandatory human review gates (Verification Gate) provide sufficient oversight for the intended use case.
Audit Metadata