codebase-onboarding

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses reconnaissance phases to identify technology stacks, architectures, and naming conventions through standard file patterns (e.g., package.json, Cargo.toml, .env.example).
  • [SAFE]: The skill instructions emphasize non-destructive operations, such as reading existing CLAUDE.md files to enhance them rather than overwriting blindly.
  • [SAFE]: The skill focuses on generating documentation (Onboarding Guide and CLAUDE.md) based on local project structure. It does not perform network operations, exfiltrate data, or execute arbitrary remote scripts.
  • [SAFE]: The use of shell commands is restricted to project discovery (e.g., ls, grep, git log) to identify patterns and directory structures, which is standard behavior for a development-oriented agent skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 02:57 PM