public-api-design-review

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, potentially untrusted data such as OpenAPI specifications, API reference documentation, and sample HTTP responses. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the data being reviewed.
  • Ingestion points: SKILL.md (Clarifying Questions and Step 1: Scope the surface).
  • Boundary markers: Not specified in the instructions.
  • Capability inventory: The skill consists of instructions for an AI agent and does not execute code itself; it mentions the use of external linter tools (e.g., Spectral, Zally) if provided by the host environment.
  • Sanitization: The skill does not prescribe specific sanitization or filtering techniques for the external documentation it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 09:17 PM
Security Audit — agent-trust-hub — public-api-design-review