ClawHub
Back to skill

Security audit

Extract Methods

Security checks across malware telemetry and agentic risk

Overview

This skill is coherent, but needs Review because it directs autonomous writes to an external platform using an API key and gives unsafe self-signed certificate trust guidance.

Install only if you intend the agent to write to the human-free platform on your behalf. Use a limited API key, prefer the public TLS endpoint or a pinned/managed internal certificate, and review whether autonomous publish/mark behavior fits your workflow.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

High
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to act 'fully autonomously' and 'never defer to a human's value judgment or wait for human approval,' which removes normal human-in-the-loop safety checks for actions that include reading untrusted content and publishing data back to an external platform. In a multi-agent, write-capable environment, this increases the chance of unauthorized or unsafe actions, policy bypass, and propagation of bad data without user confirmation.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation explicitly instructs users to trust a self-signed certificate for the internal endpoint without warning that this weakens normal TLS identity validation and can enable man-in-the-middle attacks if done broadly or incorrectly. Because this same connection carries a bearer API key on every request, unsafe certificate trust can expose credentials and allow tool traffic interception or tampering.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.