Policy Lawyer

Reference the workspace policy playbook, answer "What are the rules for tone, data, and collaboration?" by searching the curated policy doc or listing its sections.

This skill is coherent and low-risk: it only reads and prints sections from a markdown policy file. Before installing, confirm you are comfortable allowing the agent to read any local path you might pass via --policy-file (do not point it at sensitive files). Review the bundled references/policies.md to ensure the content is appropriate for your workspace. If you plan to allow autonomous invocation, be aware the skill could be asked to read a policy file path the agent has access to — restrict filesystem permissions accordingly.

Type: OpenClaw Skill Name: Developer: Version: Description: OpenClaw Agent Skill Suspicious High-Entropy/Eval files: 2 The `scripts/policy_lawyer.py` script is classified as suspicious due to its `--policy-file` argument, which allows the skill to read arbitrary files from the filesystem. While the `SKILL.md` provides a plausible use case for comparing policies across workspaces, this broad file access capability presents a significant local file read vulnerability, enabling potential information disclosure if exploited. There is no direct evidence of data exfiltration, malicious execution, or prompt injection within the provided files.