kstack-git
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [SAFE]: The skill defines a set of operational guidelines for managing Git repositories without introducing malicious behaviors.
- [DATA_EXPOSURE]: The instructions explicitly promote security hygiene by requiring the exclusion of
.tfstatefiles (which may contain secrets), temporary verification scripts, and diagnostic SQL results from commits and README files. - [COMMAND_EXECUTION]: The skill leverages the Git and GitHub CLI (
gh) for automation. It includes safety mechanisms such as requiring explicit user confirmation before merging Pull Requests and verifying CI status before reporting success. - [INDIRECT_PROMPT_INJECTION]: The skill defines a process where a subagent reviews Pull Request content. This is used as a quality control mechanism for formatting and adherence to templates, rather than a vector for untrusted instruction execution.
Audit Metadata