how
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely in a read-only mode for exploration and critique (
readonly: true), which prevents accidental or malicious modifications to the codebase during its execution. - [SAFE]: The skill relies on standard developer tools (Glob, Grep, Read) to analyze local project files. It does not perform network operations, download external scripts, or execute arbitrary code from untrusted sources.
- [SAFE]: The use of subagents (explorers, explainers, critics) is scoped to processing and synthesizing local information. The configuration for these models follows standard platform practices and involves no dynamic context injection or privilege escalation risks.
- [SAFE]: No obfuscation, hardcoded credentials, or persistence mechanisms were detected in the skill instructions or supporting templates.
Audit Metadata