ClawHub
Back to skill

Security audit

Ambiguity Resolver

Security checks across malware telemetry and agentic risk

Overview

This skill is a lightweight planning prompt that helps structure vague business problems and does not request sensitive access or perform actions on its own.

This appears suitable to install as a planning helper. Users should know it may activate on broadly worded ambiguous planning requests, so use more specific skills when a task is clearly research, execution, legal, financial, or technical implementation work.

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 skill description contains very broad trigger phrases such as "clarify a vague brief," "make sense of an unclear opportunity," and common workplace utterances like "we need to figure out what to do about X." In agentic routing systems, this can cause the skill to activate on a wide range of normal business conversations, increasing the chance of inappropriate invocation, context capture, or accidental interference with other more specific skills.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.