api-design-patterns

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary content consists of best practices, naming conventions, and structural templates for API architecture. No malicious behavioral patterns were detected.
  • [EXTERNAL_DOWNLOADS]: The documentation references standard developer utilities including @redocly/cli, openapi-typescript, and @hey-api/openapi-ts for validating specifications and generating client SDKs. These are well-known technology tools and represent safe, standard development practices.
  • [PROMPT_INJECTION]: The skill defines an indirect prompt injection surface as it processes external requirements and data models to produce API specifications.
  • Ingestion points: Untrusted data enters the agent context via 'service-requirements' and 'data-models' inputs (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the documentation.
  • Capability inventory: The skill includes 'creates-files' capabilities to output specifications and endpoint designs.
  • Sanitization: No specific sanitization or validation steps are defined for the input content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:09 PM