backend-dev

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill workflow presents a surface for indirect prompt injection by aggregating user-supplied requirements and research data into its code generation processes.
  • Ingestion points: User-provided business requirements and outputs from the 'Deep Research Agent' (SKILL.md).
  • Boundary markers: The skill does not define clear delimiters or instructions to ignore instructions embedded within the requirements or research data during the implementation phase.
  • Capability inventory: The skill possesses capabilities for complex project scaffolding, API implementation, and automated testing via '/sc:implement' and 'Playwright MCP' (SKILL.md).
  • Sanitization: No explicit sanitization or validation steps are provided for external research data before it is used to influence architectural designs or code implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:24 AM