Back to skill

Security audit

Super Mcp Integration 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a real MCP bridge, but it needs review because one approved tool can invoke many externally supplied tools without enough built-in limits.

Install only in trusted workspaces. Connect it only to MCP servers you control or trust, prefer HTTPS, avoid URL-embedded credentials, restrict the `mcp` tool to trusted/admin agents, and require separate review or confirmation before using database, account, messaging, filesystem, or other state-changing MCP tools. Do not share diagnostic reports until configuration and logs have been manually redacted.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (4)

T09 · Insecure Skill Coding Practices

Error
Location
src/index.js:15
Finding

Unrestricted MCP URLs Permit Plaintext Transmission and Unsafe Network Destinations

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Error
Location
src/index.js:129
Finding

Single MCP Tool Bypasses Fine-Grained Authorization for Dynamically Discovered Capabilities

Content
View full analysis
0 ? JSON.stringify(tools, null, 2) : 'No MCP tools available. Check server connection.' }] }; } case 'call': { if (!params.server || !para ...[truncated 3455 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
docs/TROUBLESHOOTING.md:410
Finding

Diagnostic Report Workflow Collects Configuration and Logs for External Sharing Without Automatic Redaction

Content
View full analysis
/dev/null || echo "Failed" done ``` ```markdown Run and share: ```bash chmod +x diagnose-mcp.sh ./diagnose-mcp.sh > mcp-diagnostic.txt ``` ### Support Channels 1. **GitHub Issues**: Include diagnostic report 2. **Discord**: OpenClaw Community #plugins channel 3. **Email**: Attach diagnostic report ### Useful Information to Include - OpenClaw version: `openclaw --version` - Node version: `node --version` - Plugin version: Check `package.json` - Configuration (redacted secrets) - Error logs - Steps to reproduce - Diagnostic report ``` ### Technical Analysis The supplied script copies the complete plugin configuration subtree and recent MCP-related logs into a file. The instructions then tell users to share or attach that report through public or third-party support channels. Although a later bullet says “Configuration (redacted secrets),” the script performs no redaction and the sharing instruction does not require manual inspection before publication. Depending on operator configuration and logging behavior, the report may contain: - URLs with embedded credentials. - Internal hostnames, ports, and service topology. ...[truncated 1781 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
src/http-transport.js:32
Finding

HTTP and SSE Responses Have No Time or Size Limits

Content
View full analysis
{ // ... const reader = response.body.getReader(); const decoder = new TextDecoder(); let buffer = ''; try { while (true) { const { value, done } = await reader.read(); if (done) { break; } buffer += decoder.decode(value, { stream: true }); const events = this._parseSseEvents(buffer); buffer = events.remaining; ``` ```javascript const response = await fetch(this._url, { method: 'POST', headers, body: JSON.stringify(message), signal: this._abortController?.signal }); // ... if (!response.ok) { const text = await response.text().catch(() => ''); throw new Error(`HTTP ${response.status}: ${text || response.statusText}`); } ``` ```javascript async _readSseResponse(body) { if (!body) return; const reader = body.getReader(); const decoder = new TextDecoder(); let buffer = ''; try { while (true) { const { value, done } = await reader.read(); if (done) break; buffer += decoder.decode(value, { stream: true }); const events = this._parseSseEvents(buffer); buffer = events.remaining; ``` ### Technical Analysis The transport has abort controllers for shutdown but no request deadline, idle timeout, maximum event size, maximum response size, or maximum buffered remainder. A malicious or malfunctioning server can continuously send data without an SSE event delimiter. In that case, `_parseSseEvents()` leaves the incomplete data in `remaining`, and `buffer` grows without ...[truncated 1190 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Findings (42)

MCP Config Access

High
Category
Agent Snooping
Confidence
84% confidence
Finding

Listing all MCP tools can reveal the names and capabilities of connected external services, which may expose sensitive operational context such as legal, database, or internal system integrations. In an agent environment, broad tool discovery without access controls can assist prompt-based reconnaissance and help an attacker identify higher-value tools to target next.

Content

Scanner excerpt · README.md (reported line 146)May include surrounding context.

In OpenClaw chat:

text
User: List all MCP tools

AI: I'll check what MCP tools are available.

MCP Config Access

High
Category
Agent Snooping
Confidence
80% confidence
Finding

The testing example again encourages unrestricted enumeration of MCP tools from chat, reinforcing a workflow where tool inventory is exposed through conversational access. Even in a test scenario, this pattern is risky because production users often copy examples directly, potentially enabling reconnaissance against connected systems.

Content

Scanner excerpt · README.md (reported line 433)May include surrounding context.

node test-server.js

In OpenClaw chat

User: List MCP tools

AI: [Shows available tools from test server]

text

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 · docs/CONFIGURATION.md (reported line 136)May include surrounding context.

Then reference in server

text

**Option 3: .env file**
```bash
# ~/.openclaw/.env
KR_LEGAL_API_KEY=your-api-key-here

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 · docs/CONFIGURATION.md (reported line 138)May include surrounding context.

Then reference in server

text

**Option 3: .env file**
```bash
# ~/.openclaw/.env
KR_LEGAL_API_KEY=your-api-key-here

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 · docs/CONFIGURATION.md (reported line 144)May include surrounding context.

json
{
  "envFile": "/home/user/.openclaw/.env",
  "plugins": { ... }
}

MCP Config Access

High
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · docs/REAL_EXAMPLE_KR_LEGAL.md (reported line 77)May include surrounding context.

In OpenClaw chat:

text
User: List MCP tools

AI: Let me check available MCP tools.
[Uses: mcp with action=list]

MCP Config Access

High
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · docs/REAL_EXAMPLE_KR_LEGAL.md (reported line 233)May include surrounding context.

In OpenClaw chat:

text
User: List MCP tools

AI: Let me check available MCP tools.
[Uses: mcp with action=list]

MCP Config Access

High
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · docs/TROUBLESHOOTING.md (reported line 152)May include surrounding context.

In OpenClaw chat:

text
User: List MCP tools

AI: Let me check available MCP tools.
[Uses: mcp with action=list]

MCP Config Access

High
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · docs/TROUBLESHOOTING.md (reported line 203)May include surrounding context.

In OpenClaw chat:

text
User: List MCP tools

AI: Let me check available MCP tools.
[Uses: mcp with action=list]

Instruction Override

High
Category
Prompt Injection
Confidence
70% confidence
Finding

This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Content

Scanner excerpt · README.md (reported line 412)May include surrounding context.

Diagnostic:

bash
# Enable debug mode
# Edit http-transport.js:
# new StreamableHTTPClientTransport(url, { debug: true })

Instruction Override

High
Category
Prompt Injection
Confidence
70% confidence
Finding

This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Content

Scanner excerpt · docs/TROUBLESHOOTING.md (reported line 246)May include surrounding context.

Diagnostic:

bash
# Enable debug mode
# Edit http-transport.js:
# new StreamableHTTPClientTransport(url, { debug: true })

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README explicitly demonstrates a natural-language workflow that causes an external MCP database tool to execute SQL queries, but it does not warn that such tools may reach real databases or require confirmation for destructive or sensitive operations. In an agent skill, normalizing direct database access through external tool bridges increases the chance of unsafe autonomous query execution, data exfiltration, or accidental modification if the connected MCP server exposes powerful operations.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill explicitly enables discovery and execution of external MCP tools across connected servers, which is a network-capable, potentially high-privilege integration surface, yet it declares no explicit tool scope or allowed-tools restrictions. This creates an overly broad trust boundary where an agent may invoke unexpected third-party tools or data sources without clear policy constraints, increasing the risk of data exfiltration, unintended actions, or unsafe tool use.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The front-matter description markets broad MCP connectivity to databases, APIs, legal systems, and other external services without warning that connected servers may expose sensitive, state-changing, or otherwise impactful operations. This omission can mislead users into treating all discovered tools as low-risk, when some may read confidential data or perform consequential actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs the agent to discover and call external MCP tools but does not warn users that their prompts, parameters, or retrieved data may be transmitted to third-party MCP servers. Without this disclosure, users may unknowingly expose sensitive information to external services outside the primary trust boundary.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This is a manifest JSON file, so vague-trigger review applies. The description says the plugin can 'connect to MCP servers and use their tools' but provides no specificity about when it should be invoked, what contexts it applies to, or any limiting conditions, making the activation scope overly broad for a skill manifest.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The documentation advertises a single agent-exposed tool that can enumerate and invoke arbitrary tools across multiple MCP servers, including examples like database querying, but it provides no safety guidance, permission model, or warning about sensitive/system-impacting operations. In an agent setting, this can normalize unsafe use of high-impact external capabilities and increase the chance of unintended data access, destructive actions, or prompt-driven misuse when the agent treats all discovered tools as equally safe to call.

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 · docs/CONFIGURATION.md (reported line 291)May include surrounding context.

bash
# Test URL is accessible
curl http://localhost:3000/mcp

# Test with JSON-RPC request
curl -X POST http://localhost:3000/mcp \

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The examples normalize direct querying of orders and displaying customer-linked records without any privacy guidance, access-control caveat, or data-minimization note. In an MCP integration skill, examples strongly influence agent behavior, so this can lead users or downstream agents to retrieve and expose production data more broadly than necessary.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The workflow demonstrates combining internal database-derived event information with an external weather service, but omits any warning that internal schedule/location data may be disclosed to third-party systems. Because the skill is specifically about centralized tool orchestration across MCP servers, this pattern increases the chance of unintended cross-system data sharing and privacy boundary violations.

Content

No source excerpt is available for this finding.

File System Enumeration

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.

Content

Scanner excerpt · README.md (reported line 515)May include surrounding context.

md
openclaw logs | grep MCP

# Check plugin directory
ls -la ~/.openclaw/extensions/mcp-integration/

# Test configuration syntax
cat ~/.openclaw/openclaw.json | jq '.plugins.entries["mcp-integration"]'

File System Enumeration

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.

Content

Scanner excerpt · docs/CONFIGURATION.md (reported line 347)May include surrounding context.

md
openclaw logs | grep MCP

# Check plugin directory
ls -la ~/.openclaw/extensions/mcp-integration/

# Test configuration syntax
cat ~/.openclaw/openclaw.json | jq '.plugins.entries["mcp-integration"]'

File System Enumeration

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.

Content

Scanner excerpt · docs/TROUBLESHOOTING.md (reported line 17)May include surrounding context.

md
openclaw logs | grep MCP

# Check plugin directory
ls -la ~/.openclaw/extensions/mcp-integration/

# Test configuration syntax
cat ~/.openclaw/openclaw.json | jq '.plugins.entries["mcp-integration"]'

File System Enumeration

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.

Content

Scanner excerpt · docs/TROUBLESHOOTING.md (reported line 36)May include surrounding context.

md
openclaw logs | grep MCP

# Check plugin directory
ls -la ~/.openclaw/extensions/mcp-integration/

# Test configuration syntax
cat ~/.openclaw/openclaw.json | jq '.plugins.entries["mcp-integration"]'

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 · docs/TROUBLESHOOTING.md (reported line 91)May include surrounding context.

netstat -tuln | grep 3000

Test server with JSON-RPC

curl -X POST http://localhost:3000/mcp
-H "Content-Type: application/json"
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

text