codeguard-clojure
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to interact with local development environments using standard Clojure tooling. It explicitly defines its boundaries, stating it does not collect, upload, or store user code or credentials.
- [SAFE]: All command execution is scoped to local linting (
clj-kondo) and formatting (cljstyle) tasks. The skill provides clear instructions to the agent to avoid silent installations, ensuring the user maintains control over the environment. - [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms was found. The workflow emphasizes manual review of changes and verification of tool outputs.
Audit Metadata