ClawHub
Back to skill

Security audit

markdown-formatting

Security checks across malware telemetry and agentic risk

Overview

This skill is a markdown formatting guide with broad activation terms but no executable behavior, credential use, persistence, or hidden data access.

Install this if you want agents to apply opinionated 80-column markdown formatting. Be aware it may activate for general documentation or style requests, so users who prefer different wrapping rules may want narrower triggers or a more specific formatting skill.

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
96% confidence
Finding
The trigger list contains very broad, everyday terms such as "markdown," "formatting," "documentation," and "style," plus a long natural-language trigger covering common writing activity. This can cause the skill to activate in many unrelated contexts, increasing the chance that its instructions override or interfere with other tasks and making prompt-routing less predictable.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.