ClawHub
Back to skill

Security audit

Brave Web Search

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Brave web-search skill that sends user search queries to Brave APIs and does not show hidden file access, persistence, or destructive behavior.

Install this only if you are comfortable sending search queries to Brave using the configured Brave API keys. Avoid using it for sensitive personal, credential, legal, medical, or confidential business queries unless that external sharing is acceptable in your environment.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 42)May include surrounding context.

md
- **Shell Injection Prevention**: User queries **must** be passed as discrete arguments (e.g. via `execFile` or an argv array), never interpolated into a shell command string. Concatenating user input into a shell string (e.g. `shell: true` with template literals) enables shell injection and is strictly forbidden.
- **Instruction Scope**: This skill only sends query strings to the Brave Search and Brave Summarizer APIs.
- **Environment**: It uses the `BRAVE_SEARCH_API_KEY` and `BRAVE_ANSWERS_API_KEY` provided by the OpenClaw environment.
- **Data Access**: It does not read local files or .env files. All configuration is handled by the agent.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill declares access to environment variables and makes external network requests, but it does not define an explicit tool scope such as permissions or allowed-tools. That creates an authorization ambiguity where an agent framework may grant broader capabilities than intended, making misuse or overreach harder to constrain or audit.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger condition is very broad: 'when the user wants to look something up on the web, check recent news, or get a factual answer' can match a large fraction of normal conversations. Overbroad activation increases the chance the skill runs unexpectedly, causing unnecessary outbound data sharing of user prompts to Brave APIs and potentially bypassing more appropriate or safer skills.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · index.js (reported line 1)May include surrounding context.

js
const BRAVE_API_BASE = 'https://api.search.brave.com/res/v1';

const baseHeaders = {
  'Accept': 'application/json',

Static analysis

No suspicious patterns detected.