subagent-driven-development
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a rigorous framework for executing development plans through subagents. No evidence of malicious intent, obfuscation, or unauthorized access was found.
- [COMMAND_EXECUTION]: Subagents are authorized to implement code, run tests, and perform git operations. These actions are limited to the development scope and are consistent with the skill's primary purpose.
- [PROMPT_INJECTION]: The skill processes task descriptions from external plans. Ingestion points: implementer and spec-reviewer prompts. Boundary markers: Markdown headers are used, but specific 'ignore instructions' delimiters for task bodies are not explicitly defined. Capability inventory: Subagents can modify the filesystem and execute test suites. Sanitization: No explicit sanitization of plan text is performed. Mitigation: The two-stage review process (spec compliance and code quality) provides a defensive layer against accidental or malicious instructions within task descriptions.
Audit Metadata