ClawHub
Back to skill

Security audit

Mcp Finder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward MCP-server search helper that sends user-entered search queries to a disclosed third-party API.

Install only if you are comfortable sending MCP search terms to api.rhdxm.com. Avoid putting secrets, proprietary project details, customer data, credentials, or sensitive internal context into searches.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill clearly relies on outbound network access to a third-party service, but it does not declare any explicit tool scope or permission boundary for that capability. This weakens security review and user consent because agents may invoke external communication without an up-front, machine-readable restriction or warning tied to the skill manifest.

External Transmission

Medium
Category
Data Exfiltration
Content
## REST API

```bash
curl -X POST https://api.rhdxm.com/find   -H 'Content-Type: application/json'   -d '{"query": "kubernetes monitoring", "max_results": 5}'
```

Full API docs: https://api.rhdxm.com/docs
Confidence
87% confidence
Finding
The REST API example shows that user-provided queries are transmitted to api.rhdxm.com, which is an external third party. Even though the document includes a transparency warning, this still creates a real data-exposure risk if users include sensitive prompts, internal project names, credentials, or proprietary context in their search query.

External Transmission

Medium
Category
Data Exfiltration
Content
## REST API

```bash
curl -X POST https://api.rhdxm.com/find   -H 'Content-Type: application/json'   -d '{"query": "kubernetes monitoring", "max_results": 5}'
```

Full API docs: https://api.rhdxm.com/docs
Confidence
87% confidence
Finding
The REST API example shows that user-provided queries are transmitted to api.rhdxm.com, which is an external third party. Even though the document includes a transparency warning, this still creates a real data-exposure risk if users include sensitive prompts, internal project names, credentials, or proprietary context in their search query.

External Transmission

Medium
Category
Data Exfiltration
Content
curl -X POST https://api.rhdxm.com/find   -H 'Content-Type: application/json'   -d '{"query": "kubernetes monitoring", "max_results": 5}'
```

Full API docs: https://api.rhdxm.com/docs

## MCP
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
## MCP

Connect via streamable HTTP at `https://api.rhdxm.com/mcp/` with tool: `find_server`.

## Data Transparency
Confidence
84% confidence
Finding
The MCP connection instruction directs the agent to use a remote HTTP endpoint, meaning prompts or tool arguments may be sent off-host to api.rhdxm.com. In context this is the core function of the skill, but it still presents a confidentiality and supply-chain trust risk because remote infrastructure processes the queries.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The script sends the user-provided query to a third-party API endpoint without any disclosure, consent prompt, or privacy notice. Queries may contain sensitive internal project names, credentials pasted by mistake, or other confidential context, so silent exfiltration to an external service creates a real privacy and data-handling risk.

Static analysis

No suspicious patterns detected.