NYC

Writing Plans

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): The skill is susceptible to indirect prompt injection (Category 8). It ingests untrusted design documents to generate implementation plans.
  • Ingestion points: The skill processes user-provided design specifications and codebase context during the plan creation phase.
  • Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are implemented to separate user data from the agent's logic.
  • Capability inventory: The skill writes generated plans to the local file system (docs/plans/) and encourages the use of subagents for task execution.
  • Sanitization: No evidence of sanitization or validation of the input design content before interpolation into the implementation plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:35 PM