The Agent Skills Directory

[SAFE]: The skill contains no prompt injection or instructions to bypass safety guidelines. The instructions are consistently focused on legal advisory processes and risk identification.
[SAFE]: No data exfiltration or sensitive information harvesting (e.g., credentials, environment variables, or private SSH keys) was detected. The skill does not perform any unauthorized network operations.
[SAFE]: There is no use of obfuscation techniques like Base64, zero-width characters, or homoglyphs to hide malicious payloads or instructions.
[SAFE]: The included script scripts/check-evals.py is a utility for validating the structure and content of evaluation samples. It uses only Python standard libraries (argparse, json, sys, dataclasses, pathlib) and does not execute remote code or perform external downloads.
[SAFE]: The skill maintains clear professional boundaries, explicitly stating that it does not replace a lawyer and providing specific 'upgrade boundaries' to guide users toward professional legal services in high-risk situations.

opc-legal-counsel