better-planning-build
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill is a development tool that manages local code execution and verification workflows. No malicious patterns or security risks were identified during the analysis.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local test suites and git commands (merges, pushes). These operations are gatekept by explicit human ('Architect') approval for irreversible steps and verified by multiple agent layers ('Lead' and 'Skeptic').
- [PROMPT_INJECTION]: The instructions do not contain any patterns attempting to bypass safety filters or override system constraints. The instructional language is appropriate for defining complex agent behaviors.
- [SAFE]: While the skill processes repository content and pull requests (indirect prompt injection surface), the architecture's reliance on human oversight and independent verification roles effectively mitigates potential risks from untrusted input.
Audit Metadata