awesome-api-design
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Analysis of the instructions and metadata revealed no evidence of malicious intent, obfuscation, or unauthorized data access. The documentation link in the metadata points to the author's repository on GitHub.\n- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it analyzes untrusted data like API specifications and code diffs.\n
- Ingestion points: User-provided API designs, OpenAPI/Swagger specifications, and code diffs (SKILL.md).\n
- Boundary markers: The instructions do not prescribe delimiters or warnings to isolate external data from the agent's logic.\n
- Capability inventory: The skill generates text-based designs and reviews; it does not request tools for file writing, network requests, or code execution.\n
- Sanitization: No sanitization or validation of the input specifications is mentioned.
Audit Metadata