ClawHub
Back to skill

Security audit

Skill

Security checks across malware telemetry and agentic risk

Overview

This skill is a narrowly scoped local companion integration, with token-handling caveats users should treat carefully.

Install only if you use Drakeling and are comfortable granting an agent localhost access to check status and send care actions. Treat DRAKELING_API_TOKEN as a secret: do not paste it into chats, screenshots, logs, or source control, and regenerate it if exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description and trigger language are broad enough to match ordinary conversation about pets, creatures, or checking in, which can cause the skill to activate when the user did not explicitly intend to use it. Because the skill has outbound network access and connects to a local authenticated daemon, accidental invocation could result in unintended API calls that change creature state or reveal status information.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The setup instructions tell users how to read and paste a bearer token into configuration, but do not warn that this is a sensitive credential that grants authenticated access to the local daemon. In a skill context, normalized handling of secrets increases the chance of credential disclosure through copy/paste, screenshots, logs, or unsafe storage practices, especially since the token can authorize local actions against the daemon.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The setup guide instructs users to read a locally generated API token from disk and paste it into OpenClaw configuration, but it does not warn that this token is a bearer secret that grants access to the local daemon. In a skill with outbound network permission, normalizing casual handling of the token increases the chance of accidental disclosure via screenshots, config sharing, backups, logs, or version control, which could let other local processes or exposed services authenticate to the daemon.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal