Back to skill

Security audit

Command Center

Security checks for vulnerabilities and agentic risk

Overview

This OpenClaw dashboard is mostly purpose-aligned, but its default server startup can expose sensitive session data and controls without authentication.

Review before installing. Run it only on a trusted local machine, explicitly bind to loopback if possible, and set an auth mode such as token, Tailscale, or Cloudflare before exposing the port to any network. Treat the dashboard as able to reveal recent agent conversations and to change some OpenClaw dashboard/job/topic state.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
lib/server.js:4642
Finding

Default Unauthenticated Binding Exposes Sensitive OpenClaw Dashboard Data

Content
View full analysis
pathname === p || pathname.startsWith(p + "/"), ); if (!isPublicPath && AUTH_CONFIG.mode !== "none") { const authResult = checkAuth(req, AUTH_CONFIG); if (!authResult.authorized) { console.log(`[AUTH] Denied: ${authResult.reason} (path: ${pathname})`); res.writeHead(403, { "Content-Type": "text/html" }); res.end( getUnauthorizedPage(authResult.reason, authResult.user, AUTH_CONFIG), ); return; } ``` The sensitive session endpoint is consequently reachable without authorization: ```js } else if (pathname === "/api/session") { const sessionKey = query.get("key"); if (!sessionKey) { res.writeHead(400, { "Content-Type": "application/json" }); res.end(JSON.stringify({ error: "Missing session key" })); return; } const detail = sessions.getSessionDetail(sessionKey); res.writeHead(200, { "Content-Type": "application/json" }); res.end(JSON.stringify(detail, null, 2)); ``` Although configuration declares a host, the listener ignores it: ```js server.listen(PORT, () => { const profile = process.env.OPENCLAW_PROFILE; console.log( `\u{1F99E} OpenC ...[truncated 3299 chars]
Remediation
View remediation
{ // Startup handling }); ``` 2. Use an unambiguous loopback address as the default: ```js host: process.env.HOST || fileConfig.server?.host || "127.0.0.1", ``` 3. Fail closed when a non-loopback host is selected without authentication. For example, reject startup if `auth.mode === "none"` and the configured host is not a recognized loopback address. 4. Require authentication for every endpoint that returns workspace, session, transcript, user, job, cron, memory, billing, or system information. 5. Require authentication and explicit authorization for every state-changing route. Job execution and termination should use a separate administrative authorization policy. 6. Consider replacing the global `none` mode with a loopback-only development mode that verifies the actual socket address rather than merely skipping authentication. 7. Do not rely on the startup URL as a security control. Log the actual bound address and whether authentication is enabled. 8. Add automated integration tests that: - Confirm the default listener is reachable only through loopback. - Confirm sensitive endpoints reject unauthenticated requests when listening on a non-loopback interface. - Confirm all mutating endpoints require an authorized identity. - Confirm the server refuses insecure combinations of network binding and authentication settings. ]]>

T09 · Insecure Skill Coding Practices

Error
Location
src/cerebro.js:174
Finding

Directory Traversal Permits Unintended topic.md File Modification

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (150)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Managing privacy-settings.json with local directory creation means the skill persists privacy state and can alter exposure rules, which is more sensitive than the description suggests. The main risk is silent weakening or reconfiguration of privacy boundaries.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
lib/server.js:565

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/install-system-deps.sh:50

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/linear-sync.js:495

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
src/llm-usage.js:19

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
src/openclaw.js:46

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
tests/iostat-leak.test.js:16

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
tests/server.test.js:14