repository-readme-writer

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a local utility scripts/repo_readme_probe.py used to inventory repository features. The testing script scripts/test_skill.py invokes this probe using subprocess.run with hardcoded arguments to verify its logic, representing a standard and secure implementation for local developer tooling.
  • [SAFE]: The repository inspection logic implements safety measures such as directory traversal depth limits and explicit exclusion of sensitive or temporary directories like .git, .venv, and node_modules.
  • [SAFE]: Analysis of the instructions and scripts found no evidence of network exfiltration, hardcoded credentials, or malicious prompt injection patterns.
  • [SAFE]: The skill promotes 'agent-safe' documentation standards, prioritizing stable project roles over fragile file path inventories, which mitigates the risk of agents following outdated or misleading instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 10:45 AM
Security Audit — agent-trust-hub — repository-readme-writer