public-api-design-review
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill functions purely as an architectural auditing guide and does not include executable code or requests for dangerous permissions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data, specifically API specifications and sample HTTP responses provided by users. While this creates a theoretical surface for indirect prompt injection (e.g., hidden instructions within an OpenAPI description), the risk is mitigated as the skill does not use tools capable of executing commands or exfiltrating data.
- Ingestion points: The skill processes external OpenAPI specifications, reference documentation, and production response samples (SKILL.md, Section 1).
- Boundary markers: The instructions do not explicitly define delimiters to separate user data from system instructions, which is common in text-auditing skills.
- Capability inventory: The skill frontmatter does not request access to network tools, file-writing utilities, or shell execution environments.
- Sanitization: No specific input sanitization instructions are present, as the skill relies on the agent's internal safety filters.
Audit Metadata