ClawHub
Back to skill

Security audit

OpenClaw Temperature

Security checks across malware telemetry and agentic risk

Overview

The skill mostly matches its GIF-reaction purpose, but it stores and can display a generated service API key in ways users should review before installing.

Install only if you are comfortable using the publisher's hosted GIF API. Keep metadata summaries short and non-sensitive, treat the generated API key as a secret, and avoid sharing recharge or debug output until the key is masked or the recharge path is removed.

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 (4)

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The document explicitly promotes automatic API key registration and local storage but provides no indication of user notice, consent, or opt-in controls. Even if the key is only for a hosted GIF service, silently creating and persisting credentials can violate user expectations, obscure account creation/data handling, and increase privacy and trust risks if the remote service changes behavior or the key is later reused.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill persists the API key to localStorage in browser contexts or to a plaintext JSON file in Node without encryption, permission hardening, or any user-facing disclosure. This creates a real secret-handling weakness because other local code, browser scripts, shared-user environments, backups, or accidental file disclosure can expose the bearer token and allow unauthorized use of the remote service.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The code sends a reaction-decision payload to a third-party hosted endpoint, and that payload is built from conversation-derived fields such as userMessage, mainReply, toolSummary, conversationSummary, and metadata. Even if intended for harmless emotion/reaction generation, transmitting conversation context off-device without explicit disclosure or consent can leak sensitive user content, prompts, errors, or operational details to the remote service.

Ssd 3

High
Confidence
98% confidence
Finding
The recharge markdown includes `recharge.apiKey` directly in user-visible output, which can expose the full stored bearer token in chat transcripts, logs, screenshots, rendered markdown, or downstream integrations. Because the key is used for authorization to the hosted API, disclosure enables token theft and unauthorized API access or account abuse.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
tests/index.test.js:96