blast-radius
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or data exfiltration behaviors were detected. The skill's operations are consistent with its stated purpose of code analysis.\n- [COMMAND_EXECUTION]: The skill instructs the agent to use git, grep, rg, and find to analyze the local repository. It also attempts to locate and execute a local Python script (graph_query.py) within a specific plugin directory (~/.claude/plugins/gauntlet/). These actions are performed on the local filesystem and do not involve untrusted remote sources.
Audit Metadata