ClawHub
Back to skill

Security audit

Openclaw Cc Rules

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed programming-workflow ruleset that mainly tells the agent to plan, read code, avoid risky Git actions, and verify changes.

Install this if you want OpenClaw to automatically apply a conservative coding workflow in programming sessions. Review or narrow the activation rules if you prefer explicit opt-in, and avoid cloning the third-party GitHub source unless you have inspected it.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

High
Confidence
90% confidence
Finding
The trigger phrase says the skill will auto-apply to essentially anything involving programming, which is overly broad for a persistent agent skill. In practice, this can cause the skill to activate in unintended contexts, override more specific instructions, and steer agent behavior across many sessions without clear user intent.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The README says the skill activates whenever OpenClaw detects a 'programming-related scenario' but never defines that boundary. Ambiguous activation logic in a globally installed skill can lead to unexpected instruction injection into unrelated or partially related conversations, reducing user control and increasing prompt-scope risk.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation conditions are very broad and cover routine development tasks such as coding, debugging, review, and Git operations. That can cause the skill to auto-trigger in many normal conversations, unexpectedly imposing workflow constraints and tool-use guidance on unrelated tasks.

Static analysis

No suspicious patterns detected.