api-lifecycle

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the transformation of user-provided interview responses into generated OpenAPI specifications and Laravel source code, creating an attack surface for indirect prompt injection.\n
  • Ingestion points: Data enters the context via the 'API Discovery Interview' blocks in the /api design command (SKILL.md, Section 1.1).\n
  • Boundary markers: None. The instructions do not define delimiters or provide warnings to the agent regarding potential instructions embedded within the user data.\n
  • Capability inventory: The skill writes multiple PHP files (Controllers, Models, Policies, Migrations) and encourages the execution of these files via the Laravel CLI tool.\n
  • Sanitization: None. The prompt does not require the agent to validate or escape the user's input before interpolating it into the generated code templates.\n- [COMMAND_EXECUTION]: The skill instructs the agent to facilitate the execution of local system commands for database management and testing.\n
  • Evidence: Instructions in sections 2.9 and 3.5 of SKILL.md prompt the user to execute php artisan migrate and php artisan test.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:55 PM
Security Audit — agent-trust-hub — api-lifecycle