ClawHub
Back to skill

Security audit

Quick Plan

Security checks across malware telemetry and agentic risk

Overview

This skill is a planning helper that reads project context and writes a markdown implementation plan only after approval.

Before installing, be aware that the skill may activate on casual planning requests in an implementation discussion and may read relevant project files to prepare a draft. Review the generated plan before approving any save to `.beagle/plans/`.

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
90% confidence
Finding
The skill advertises trigger phrases such as "plan it" and "plan this out," which are common conversational phrases that may appear in ordinary discussion without the user intending to invoke this specific skill. In an agentic environment, that can cause unintended activation, leading the system to generate and possibly write planning artifacts when a different action was desired.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal