ClawHub
Back to skill

Security audit

update-readme

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed README refresh workflow; its broad triggers are worth noticing but the behavior stays scoped to documentation work.

Before installing, be aware that this skill may activate on general documentation or research requests. Use it for intentional README restructuring, and review any proposed README edits and web-researched citations before accepting them.

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
88% confidence
Finding
The trigger list includes generic terms such as "readme", "documentation", "research", and "structure", which are likely to match many normal conversations and unrelated tasks. In an agent environment, this can cause the skill to activate too broadly, leading to unintended execution of repository inspection, web research, and file modification workflows when the user did not explicitly request this skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.