ClawHub
Back to skill

Security audit

OpenSpec

Security checks across malware telemetry and agentic risk

Overview

This is a coherent OpenSpec workflow helper, with disclosed project file changes and an external CLI install that users should review.

Install this only if you trust the OpenSpec npm package. For sensitive projects, consider pinning a specific CLI version, use version control, review generated openspec/ and .claude/skills/ files, and confirm before accepting implementation edits or running archive commands.

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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger description is broad enough to activate on common development requests like feature planning, refactoring, or structured work, which can cause the skill to run in situations the user did not explicitly intend. In an agent setting, overbroad invocation increases the chance of unsolicited workflow changes, command suggestions, or file-modifying behavior being introduced into otherwise ordinary requests.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to create artifact files under openspec/changes/<name>/ and proceed through implementation without requiring user notification or confirmation before filesystem modification. In practice, this can lead to silent writes, project structure changes, or unintended repository modifications, especially when combined with the broad activation scope of the skill.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.