claude-code-agents

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill's instructions and templates focus on providing a framework for creating specialized subagents. No malicious prompt injection patterns, data exfiltration logic, or persistence mechanisms were detected.
  • [COMMAND_EXECUTION]: The skill includes two Python helper scripts (validate-agent-frontmatter.py and lint-agent-description.py) intended for validating subagent configurations. These scripts use yaml.safe_load to prevent unsafe deserialization and perform standard static analysis on file metadata.
  • [EXTERNAL_DOWNLOADS]: Several reference files link to official documentation at code.claude.com. These are legitimate references to a well-known service and do not involve untrusted remote code execution or dangerous downloads.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 06:18 AM
Security Audit — agent-trust-hub — claude-code-agents