v-build
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats identified. The skill focuses on standard software engineering workflows, including git operations, PR management, and code review processes.
- [COMMAND_EXECUTION]: The skill instructs the agent to perform standard development tasks such as
gitoperations (branching, committing, pushing), and execution of local verification tools liketypecheckandlint. These are appropriate for the intended use case of building software features within a repository. - [INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided feature requests, it mitigates risk by requiring the agent to decompose the request into structured briefs and contracts before dispatching to subagents. This architectural approach limits the direct flow of untrusted input into execution contexts.
Audit Metadata