Openclaw Marshal

Compliance and policy enforcement for agent workspaces. Define security policies, audit compliance, check command restrictions, and generate audit-ready reports. Free alert layer — upgrade to openclaw-marshal-pro for active enforcement, blocking, and automated remediation.

This tool appears to be a local compliance/audit script and is mostly coherent with its description, but it can modify your workspace (quarantine/enforce/hooks). Before installing or running it: 1) Treat the package as untrusted until you verify its source—there is no homepage or known repo in the metadata. 2) Inspect the bundled scripts yourself (search for functions named enforce, quarantine, protect, os.remove, shutil.rmtree, os.rename, subprocess/os.system) to confirm what modifications will occur and when. 3) Run on a copy or non-production workspace first and back up your workspace. 4) If you intend to let agents call this skill autonomously, restrict or review agent permissions (or set disable-model-invocation) so it cannot run destructive commands without human approval. 5) Ask the publisher for a canonical source/repo and change logs; prefer installing from a verified repository. If you want help locating and reviewing the parts of scripts/marshal.py that implement quarantine/enforce, I can inspect those functions in more detail.

Type: OpenClaw Skill Name: openclaw-marshal Version: 1.0.2 The OpenClaw Marshal skill is a security and compliance tool designed to audit other skills and the workspace against defined policies. It scans for dangerous command patterns (e.g., RCE risks like `curl|bash`, `eval()`, `os.system`), network policy violations, and configuration issues. Its 'Pro' features include active enforcement by quarantining non-compliant skills (renaming their directories) and generating defensive runtime hooks for agent environments to block dangerous commands or PII leaks. All operations are aligned with its stated security purpose, and there is no evidence of intentional malicious behavior such as data exfiltration, backdoor installation, or unauthorized remote control. The code adheres to its claim of 'No External Dependencies' and 'No network calls'.