ClawHub
Back to skill

Security audit

Skill安全审查(免费版)

Security checks across malware telemetry and agentic risk

Overview

This skill is a local checklist-style security review aid, with some sloppy trigger wording but no hidden persistence, credential use, or exfiltration behavior in the artifact.

Install only if you want a local, manual Skill security-review checklist. When using it, point scans at the specific skill directory being reviewed, not your home folder or credential/config directories, and ignore the generic data-analysis trigger wording unless you are actually doing security vetting.

SkillSpector

By NVIDIA
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 (1)

Vague Triggers

High
Confidence
78% confidence
Finding
The trigger conditions are unrelated to the skill's stated security-audit purpose and instead target broad data-analysis/reporting scenarios. In an agent ecosystem, overbroad triggers can cause the skill to activate in inappropriate contexts, increasing the chance that it gains access to unrelated inputs or influences workflows where users did not intend a security-audit tool to run.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.