Back to skill

Security audit

Clawbrain Boost

Security checks for vulnerabilities and agentic risk

Overview

The skill is not clearly malicious, but it asks users to make a third-party model provider the default and advertises automatic long-term memory without enough data-handling disclosure or controls.

Review before installing. Use this only if you are comfortable sending default OpenClaw model requests, including possible text, images, conversation context, and memory-derived information, to the ClawBrain/FactorHub endpoint. Prefer a dedicated revocable API key, avoid regulated or secret data, keep your existing default model unless you intentionally want global routing, and look for clear retention, deletion, opt-out, and privacy terms from the publisher.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

other

Warning
Location
SKILL.md:63
Finding

Global Redirection of Agent Requests to a Third-Party Model Provider Without Privacy Safeguards

Content
View full analysis
Remediation
View remediation
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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest description is written entirely in Chinese and presents the skill as generally user-invocable, but it does not state that the skill is Chinese-only or offer any language/locale choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises automatic memory extraction, identity updates, history retrieval, and daily consolidation, but it does not clearly disclose what user data is stored, where it is stored, how long it is retained, or how users can disable or delete it. Because these features imply persistent collection and processing of potentially sensitive conversational data, the missing privacy warning creates a real risk of unconsented retention and exposure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The configuration instructs users to route model traffic to a third-party endpoint at api.factorhub.cn and supply an API key, but the skill does not clearly warn that prompts, conversation content, and possibly attachments will be transmitted to that external provider. This is dangerous because users may assume the skill is purely local or first-party and unknowingly send sensitive data to an undisclosed external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The skill explicitly configures an external API endpoint, which means user prompts and model interactions are transmitted outside the local environment. In this skill's context, the risk is amplified by the advertised memory and conversation-processing features, because sensitive historical context may also be included in outbound requests to the third party.

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

md
"models": {
    "providers": {
      "clawbrain": {
        "baseUrl": "https://api.factorhub.cn/v1",
        "apiKey": "你的 API Key",
        "api": "openai-completions",
        "models": [