skills/hubvue/skills/api-generator/Gen Agent Trust Hub

api-generator

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill instructions. The instructions emphasize incremental, additive changes and strictly follow existing project conventions.
  • [PROMPT_INJECTION]: While the skill processes user-provided API specifications which could serve as an indirect injection vector, the risk is mitigated by a mandatory 'Plan Mode' requiring human approval before code generation occurs.
  • Ingestion points: Processes user-supplied API methods, paths, and schemas defined in Phase 3 and Interview Mode.
  • Boundary markers: Implements a mandatory Phase 2 'Plan Mode' and requires explicit user approval before execution.
  • Capability inventory: Generates (writes) request functions, types, mock handlers, and test artifacts.
  • Sanitization: Relies on human-in-the-loop verification of the generated plan to prevent unintended modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 07:23 AM
Security Audit — agent-trust-hub — api-generator