NYC

subagent-driven

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (SAFE): The skill defines a process where external 'plan' data is ingested and interpolated into subagent prompts. While this is the primary purpose of the skill, it creates a surface for indirect prompt injection if the plan contains malicious instructions.
  • Ingestion points: Plan text is extracted in Step 1 and interpolated in Steps 2a (Implementer), 2c (Spec Reviewer), and 3 (Final Reviewer).
  • Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are included in the prompt templates.
  • Capability inventory: The subagents described in the skill are expected to write code, modify files, and execute tests (TDD).
  • Sanitization: The skill lacks explicit sanitization or validation logic for the plan text before it is passed to subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM