ClawHub
Back to skill

Security audit

spec-writing

Security checks across malware telemetry and agentic risk

Overview

This skill is a markdown-only guide for writing clear feature specifications and does not request sensitive access or perform actions on the user’s system.

Install this if you want structured help drafting feature specifications. Be aware it may activate on general requirements discussions because of broad triggers, but the reviewed files contain only documentation-style guidance and templates.

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
93% confidence
Finding
The trigger list includes very broad, common terms such as 'specification', 'requirements', and 'acceptance-criteria', which can cause the skill to activate in many unrelated contexts. This can lead to unintended invocation, context confusion, and inappropriate guidance being injected into conversations, especially when users are discussing requirements at a high level rather than explicitly requesting this skill.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.