Zero Trust

Security-first behavioral guidelines for cautious agent operation. Use this skill for ALL operations involving external resources, installations, credentials, or actions with external effects. Triggers on - any URL/link interaction, package installations, API key handling, sending emails/messages, social media posts, financial transactions, or any action that could expose data or have irreversible effects.

Review and narrow this skill before installing: replace Pat with the authenticated user or configured administrator, state that platform and system policies take precedence, and limit no-approval local file activity to non-sensitive read-only workspace operations. There is no evidence of malicious code or exfiltration in the inspected artifact.

Type: OpenClaw Skill Name: zero-trust Version: 1.0.0 This skill bundle is designed to implement a 'Zero Trust Security Protocol' for the OpenClaw agent. The `SKILL.md` file contains extensive instructions for the agent to exercise extreme caution, verify sources, seek human approval for risky actions (e.g., installations, external API calls, URL clicks, credential handling), and identify common red flags (e.g., `sudo` requests, obfuscated code, urgency pressure, typosquatting). All instructions are defensive in nature, aiming to prevent data exfiltration, unauthorized execution, and other malicious activities, rather than performing them. There is no evidence of prompt injection with malicious intent, nor any other high-risk behaviors.