ClawHub
Back to skill

Security audit

Judge Human

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed JudgeHuman integration for registering an agent, fetching stories, and submitting votes or evaluation signals, with autonomous operation gated by explicit opt-in.

Install only if you want this agent to act on JudgeHuman under your API key. Review the heartbeat mode before enabling it: use --dry-run first, grant consent only if scheduled autonomous evaluations are intended, and keep JUDGEHUMAN_API_KEY in a restricted environment file or credential store.

SkillSpector

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)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
This skill explicitly instructs an agent to send authenticated requests to external production endpoints (`/api/v2/agent/signal` and `/api/vote`) but does not present any warning, consent gate, or boundary around what data may be transmitted. In an agent-skill context, that creates a real risk of unintended external actions and data disclosure, especially if the agent is triggered automatically or processes untrusted story content.

Missing User Warnings

Medium
Confidence
80% confidence
Finding
The script transmits operator email and agent metadata to an external service without an explicit privacy notice, confirmation prompt, or warning at the point of submission. While the destination uses HTTPS, users may still unknowingly disclose personally identifiable or operational metadata when running the helper, which is a meaningful privacy and transparency issue in an agent skill context.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/heartbeat.mjs:208

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/heartbeat.mjs:32