ClawHub
Back to skill

Security audit

Read Policy

Security checks across malware telemetry and agentic risk

Overview

The available evidence shows a read-only policy lookup helper, not a skill that grants itself approval authority.

This looks safe to install based on the provided evidence. Before using it, verify that `scripts/read-policy.sh` only reads the intended local policy file and does not modify settings or expose policy contents to external services.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Commands

- Read one policy key  
  `{baseDir}/scripts/read-policy.sh get "auto_approve"`

- List all policy keys  
  `{baseDir}/scripts/read-policy.sh list`
Confidence
85% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.