subagent-driven-development
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behavior, obfuscation, or data exfiltration attempts were found. The skill follows established patterns for multi-agent development workflows.
- [INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted data from implementation plans and subagent reports. However, it incorporates security best practices by including a 'Spec Compliance Reviewer' specifically tasked with independent verification. This reviewer is explicitly instructed to 'Not Trust the Report' and 'Read the actual code', which serves as a defensive gate against potential manipulation or hallucinations from the implementation phase.
Audit Metadata