claude-compass-best-practices
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a documentation and architectural guide for a specific project. It does not include any commands for remote code execution, data exfiltration, or prompt injection.
- [SAFE]: It explicitly emphasizes security by mandating the use of parameterized queries to prevent SQL injection within the references/database-patterns.md file.
- [SAFE]: The CLI commands and library recommendations (tree-sitter, knex) are standard for the described development environment and do not involve untrusted or suspicious sources.
Audit Metadata