api-implementation

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted external data to generate executable code.
  • Ingestion points: Processes openapi_spec (YAML) and design_spec (Markdown) to create implementation files.
  • Boundary markers: The instructions lack explicit boundary markers or directives to the agent to disregard natural language instructions found within the input documents.
  • Capability inventory: The skill produces TypeScript source code for controllers and services, which may be automatically saved or committed to a repository.
  • Sanitization: There is no mention of sanitizing or validating the input specifications to ensure they only contain data and not malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 04:54 AM