subagent-driven-development
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious prompt injection, data exfiltration, or unauthorized command execution patterns were identified.
- [SAFE]: The skill follows secure orchestration practices by using fresh subagents with isolated context for each task and requiring independent verification of all generated code.
- [SAFE]: File access and git operations are conducted within an implementation workflow that explicitly requires user consent for major operations like starting on the main branch.
- [SAFE]: References to external skill templates (e.g., react-native-hifi:*) appear to be part of a legitimate and integrated development suite.
Audit Metadata