Openclaw Shield 1.0.3

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:20 PM UTC
• Version:
  1.0.0

Overview

This appears to be a security-review skill with broad activation wording, but the supplied evidence does not show hidden, destructive, persistent, or data-exfiltrating behavior.

Install only if you want this skill to be available for security and code-audit tasks. The publisher should ideally narrow its activation wording so ordinary security-related discussion does not invoke it unexpectedly.

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 (1)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The activation guidance lists broad phrases like "security scanning," "threat detection," and "code auditing" without defining boundaries, exclusions, or concrete trigger phrases. In a skill-routing context, this can cause unintended invocation for many generic security or auditing requests.

VirusTotal

66/66 vendors flagged this skill as clean.