Openclaw Cc Rules Gitee

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:34 PM UTC
• Version:
  1.0.1

Overview

This skill is a visible coding-workflow ruleset that broadly affects programming sessions but does not include hidden code, credential access, exfiltration, or destructive behavior.

Install this only if you want OpenClaw to consistently apply this structured workflow in coding sessions. Expect it to influence future programming conversations until removed or disabled, and inspect the external GitHub repository first if installing by clone rather than from the reviewed artifact.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

High

• Confidence: 89% confidence
• Finding: The README states the skill will automatically invoke for essentially any programming-related content, which is an overly broad trigger surface. Broad auto-activation increases the chance that the skill overrides user expectations, interferes with unrelated tasks, or applies risky coding/git behaviors in contexts where explicit opt-in and scope checks should be required.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: Saying the skill activates whenever OpenClaw detects 'programming-related scenarios' is ambiguous and lacks bounded scope. In agent systems, vague trigger rules can cause unexpected behavior carryover into sensitive sessions, especially when the skill later prescribes edits, planning constraints, and git operations.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The skill auto-activates for very broad categories like coding, debugging, review, Git operations, and project setup, which are common requests. This can cause the skill to override or steer many unrelated sessions without explicit user consent, increasing the chance that its operational constraints or behaviors are applied unexpectedly.

VirusTotal

65/65 vendors flagged this skill as clean.