codebase-onboarding
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses local reconnaissance patterns (searching for package manifests like
package.json,go.mod, etc.) to identify project tech stacks. - [SAFE]: It instructs the agent to analyze directory structures, naming conventions, and code patterns to generate local documentation (
CLAUDE.md). - [SAFE]: No external network requests, data exfiltration patterns, or privilege escalation commands are present in the skill instructions.
- [SAFE]: The reconnaissance phase uses standard directory traversal (ignoring sensitive folders like
.git) and glob/grep patterns for code analysis, which is appropriate for its stated purpose.
Audit Metadata