subagent-driven-development

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection attacks where malicious instructions embedded in implementation plans could be executed by subagents.
  • Ingestion points: Implementation plans (referenced as docs/plans/feature-plan.md in examples) are read in SKILL.md and their content is interpolated into prompts for subagents in implementer-prompt.md and spec-reviewer-prompt.md.
  • Boundary markers: Absent. The task text is inserted into prompts without specific delimiters or instructions to the subagents to ignore potential instructions embedded within the plan text.
  • Capability inventory: The implementer subagent is granted capabilities to modify the codebase, write and execute tests, and perform git commits via the general-purpose tool and environment access.
  • Sanitization: Absent. No evidence of validation or filtering is performed on the content of the plan files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 10:10 PM