subagent-driven-development

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external implementation plans, creating a surface for indirect prompt injection where instructions within a plan could potentially influence subagent behavior.
  • Ingestion points: SKILL.md describes reading external plan files (e.g., docs/plans/feature-plan.md) to extract task descriptions.
  • Boundary markers: Present in implementer-prompt.md and spec-reviewer-prompt.md using markdown headers to isolate task data.
  • Capability inventory: implementer-prompt.md grants subagents capabilities to modify files and perform git commits.
  • Sanitization: Absent; the skill does not perform explicit sanitization of plan content before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 10:48 AM