ClawHub
Back to skill

Security audit

technical-writer

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only technical writing helper with no executable install code or sensitive access in its artifacts.

This skill appears safe to install as a documentation assistant. Review generated documentation before publishing, especially drafted commands, API examples, authentication descriptions, or upgrade steps, because writing helpers can still produce inaccurate or overly broad content.

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
83% confidence
Finding
The skill description uses very broad activation language ('Use when') without clear scope boundaries or exclusions, which can cause the agent to invoke this skill in situations beyond pure technical writing. Over-broad routing increases the chance that unrelated or sensitive tasks are handled by a documentation-oriented skill, potentially leading to inappropriate authority, confused delegation, or unsafe handling of mixed-content requests.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.