ClawHub
Back to skill

Security audit

write-goal

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward goal-writing helper with no executable code, hidden data access, or unrelated privileges.

Before installing, consider that this skill can help commit structured goals when goal-management tools are available. Review the objective, completion criterion, boundary, and any budget before accepting or replacing an active goal.

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
91% confidence
Finding
The trigger phrases are broad, common-language commands that can match ordinary conversation outside the narrow intent of goal-authoring. This can cause unintended skill activation, steering the agent into autonomous-goal setup when the user may only be discussing goals conceptually, increasing the chance of workflow confusion or unsafe delegation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.