Back to skill

Security audit

ClawBrain Doctor

Security checks for vulnerabilities and agentic risk

Overview

This is a small diagnostic skill whose outbound curl examples are disclosed and aligned with its stated OpenClaw/ClawBrain health-check purpose.

Install only if you intend to use ClawBrain/OpenClaw diagnostics. Before running the curl checks, verify that api.factorhub.cn is the service endpoint you trust and use a scoped token rather than a broad account credential.

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
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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The natural-language description and usage instructions force a single language/locale experience by presenting the skill entirely in Chinese and specifying Chinese trigger phrases only. There is no indication that users may choose another language or that the locale restriction is intentional and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation guidance says users can trigger the skill by saying “诊断一下” or “检查配置”. Both phrases are generic, everyday requests that could easily appear in unrelated conversations, and the file does not provide scope limits or negative examples to clarify when the skill should or should not activate.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The skill is configured with command-dispatch to an exec tool and includes explicit curl commands to an external domain using a bearer token. This creates a real data-transmission path to a third-party service, and if executed in-context could expose API credentials and system/service metadata outside the local trust boundary.

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

bash
# 检查后端模型健康状态
curl https://api.factorhub.cn/v1/health/backends -H "Authorization: Bearer YOUR_KEY"

# 检查知识图谱状态
curl https://api.factorhub.cn/v1/graph/stats -H "Authorization: Bearer YOUR_KEY"

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This command transmits knowledge-graph status information to an external API endpoint with authorization credentials. In a diagnostic skill, that increases sensitivity because operational metadata and authenticated access may be exposed to a remote service if the command is run automatically or without clear consent.

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

md
curl https://api.factorhub.cn/v1/health/backends -H "Authorization: Bearer YOUR_KEY"

# 检查知识图谱状态
curl https://api.factorhub.cn/v1/graph/stats -H "Authorization: Bearer YOUR_KEY"

# 检查模型列表和能力
curl https://api.factorhub.cn/v1/models -H "Authorization: Bearer YOUR_KEY"

External Transmission

Medium
Category
Data Exfiltration
Confidence
82% confidence
Finding

The model-list query is another outbound authenticated request to an external service. Although model metadata is less sensitive than some other data, the presence of executable network instructions plus bearer-token usage still represents a genuine external transmission risk in an agent skill context.

Content

Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.

curl https://api.factorhub.cn/v1/graph/stats -H "Authorization: Bearer YOUR_KEY"

检查模型列表和能力

curl https://api.factorhub.cn/v1/models -H "Authorization: Bearer YOUR_KEY"

text

接入 ClawBrain:https://clawbrain.dev/dashboard