ClawHub
Back to skill

Security audit

Security Hardening

Security checks across malware telemetry and agentic risk

Overview

This is a coherent security-audit skill, but users should treat its reports as sensitive because it may inspect and record secrets or personal data found in the workspace.

Install only if you want an agent to inspect the current workspace for secrets, PII, and security weaknesses. Before running it, confirm the workspace boundary, request redacted findings, review any proposed config edits, and enable heartbeat or cron audits only if you intentionally want ongoing scans.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrase is very generic and overlaps with ordinary user requests such as asking an agent to 'run a security audit.' That can cause accidental invocation of the full skill in situations where the user intended a narrower review, expanding file scanning behavior and potentially producing or storing sensitive audit outputs unnecessarily.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs saving a security audit report to a persistent memory file, and that report is likely to contain sensitive findings such as secret locations, PII references, and configuration weaknesses. Persisting that data without a prominent warning, minimization guidance, or redaction requirement increases the blast radius if memory files are later synced, shared, or exposed.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.