subagent-driven-development

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill carries a risk of indirect prompt injection due to its reliance on external data sources for agent instructions.
  • Ingestion points: The skill ingests untrusted data from implementation plans, such as docs/plans/feature-plan.md, to extract task details and context.
  • Boundary markers: The workflow lacks clear delimiters or explicit instructions to subagents to treat the ingested plan content as data rather than instructions.
  • Capability inventory: The subagents dispatched by this skill have the authority to write code, execute shell commands for testing, and perform git commits.
  • Sanitization: There are no documented steps for sanitizing, escaping, or validating the content of implementation plans before they are interpolated into subagent prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 03:46 AM