ClawHub
Back to skill

Security audit

Nix Run

Security checks for vulnerabilities and agentic risk

Overview

The skill is not clearly malicious, but it asks the agent to route too much command-line work through a package-fetching shell wrapper.

Review before installing. Use this only if you intentionally want command-line tools routed through a package-fetching wrapper, and avoid relying on it for secrets, account changes, destructive file operations, financial workflows, or commands that should require explicit confirmation. Ask the publisher to narrow activation rules and document exclusions.

SkillSpector

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
89% confidence
Finding
The skill is framed as applicable to virtually any CLI action, which encourages indiscriminate invocation. Overbroad activation increases the chance the agent will route sensitive, destructive, or unnecessary commands through a package-fetching shell wrapper without user awareness or context-specific safety checks.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The instructions mandate use for all CLI tools and suppress normal decision-making about whether the skill should activate. This can override safer defaults, causing the agent to invoke a shell-capable wrapper in situations where direct execution, user confirmation, or refusal would be more appropriate.

Static analysis

No suspicious patterns detected.