ClawHub
Back to skill

Security audit

Muguozi1 Openclaw Security Auditor

Security checks across malware telemetry and agentic risk

Overview

This is a security-review guidance skill with overstated test/quality claims, but its behavior is disclosed and there is no evidence of hidden access or harmful actions.

Reasonable to install as an advisory security checklist. Do not treat the badges, optimization claims, or test script as proof of real validation or audit coverage; invoke it intentionally for security review tasks and verify its recommendations against your own code and policies.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Intent-Code Divergence

Medium
Confidence
96% confidence
Finding
The test functions are placeholders that always report success and return True without validating any behavior. In a security-auditor skill, fake passing tests are especially risky because they can create false assurance that security checks or protections work when they have never actually been exercised.

Vague Triggers

Medium
Confidence
77% confidence
Finding
The trigger list is broad enough that the skill may activate in many general contexts involving authentication, secrets, or validation. In an agent environment, unintended invocation can expand the skill's influence over sensitive workflows and cause over-collection, overreach, or inappropriate security guidance in contexts where it was not intended.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:91