subagent-driven-development
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of implementation plans.
- Ingestion points: The skill reads and processes external implementation plans (e.g., 'feature-plan.md') to define subagent tasks.
- Boundary markers: There are no explicit markers or instructions to help the agent distinguish between task data and potential instructions embedded within the plan.
- Capability inventory: The skill orchestrates subagents with the ability to write code, execute local tests, and perform git commits.
- Sanitization: No sanitization or validation of the plan content is performed before it is passed to subagents.
- Autonomy: The skill specifically instructs the agent to 'not pause to check in with your human partner between tasks,' which significantly increases the autonomy of the agent and reduces user oversight when processing potentially untrusted plan data.
Audit Metadata