ClawHub
Back to skill

Security audit

OpenClaw Optimised

Security checks across malware telemetry and agentic risk

Overview

This is a small instruction-only guide for writing CLAUDE.md files, with no code, install hooks, credential use, or hidden behavior.

This skill is reasonable to install as a CLAUDE.md writing guide. Review any CLAUDE.md or .claude/rules content it helps create, because those files can influence future agent behavior; avoid secrets, broad standing instructions, or rules that should not persist.

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
86% confidence
Finding
The skill description uses very broad activation criteria such as creating, reviewing, or discussing CLAUDE.md best practices, which could cause the agent to invoke this skill for many ordinary requests. Over-broad triggering increases prompt-surface area and can unintentionally steer unrelated conversations, creating opportunities for instruction interference or policy overshadowing even though the skill content itself is not overtly malicious.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.