ClawHub
Back to skill

Security audit

hooks-eval

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for evaluating Claude/OpenClaw hooks, with no executable install behavior or hidden data access.

Install this if you want reference guidance for evaluating hook security, performance, and SDK compliance. Expect that it may activate in some general security or performance conversations because of broad triggers; consider narrowing triggers if that becomes distracting.

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

Medium
Confidence
91% confidence
Finding
The trigger list includes broad generic terms such as "hooks", "evaluation", "security", and "performance", which can cause this skill to be invoked in many unrelated contexts. Because this skill is advisory and security-oriented, unintended invocation can inject unnecessary guidance into unrelated workflows, increase prompt surface area, and create confusion or misrouting during sensitive audits.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.