ClawHub
Back to skill

Security audit

fable-method

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed problem-solving workflow skill with broad but purpose-aligned activation guidance and no hidden execution, persistence, or data handling.

Install this if you want agents to use a disciplined multi-step workflow by default when no narrower skill applies. Be aware it may influence many complex coding or investigation tasks, so users who prefer only explicitly invoked skills may want to adjust the activation wording.

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

High
Confidence
96% confidence
Finding
The skill explicitly says it should be used "proactively when starting any multi-step task that no task-specific skill covers," which is an overly broad activation trigger. In an agentic system, this can cause the skill to insert itself into many unrelated workflows, potentially overriding narrower safety boundaries or changing agent behavior in contexts where it was not explicitly requested, increasing prompt-scope and control-surface risk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.