ClawHub
Back to skill

Security audit

Meyhem Researcher

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed research helper that sends search terms and selected result URLs to api.rhdxm.com, with no evidence of hidden local access or persistence.

Install only if you are comfortable sending your research queries, chosen agent_id, and selected result URLs to api.rhdxm.com. Do not include secrets, private business information, or proprietary research topics in queries unless that external service is acceptable for your use case.

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
94% confidence
Finding
The skill clearly performs network operations to a third-party service, but the manifest does not declare any explicit tool scope such as permissions or allowed-tools. That creates a transparency and policy-enforcement gap: users and hosting platforms may not realize the skill can exfiltrate user-provided content to an external endpoint.

External Transmission

Medium
Category
Data Exfiltration
Content
## Quick Start (REST)

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

```bash
curl -s -X POST https://api.rhdxm.com/search \
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
Full API docs: https://api.rhdxm.com/docs

```bash
curl -s -X POST https://api.rhdxm.com/search \
  -H 'Content-Type: application/json' \
  -d '{"query": "YOUR_QUERY", "agent_id": "my-researcher", "max_results": 10, "freshness": "hour"}'
```
Confidence
90% confidence
Finding
The URL in the curl example identifies a concrete third-party endpoint receiving submitted research queries and metadata such as agent_id. Even though the file discloses this behavior, it still represents outbound transfer of user-controlled content to an external service, with associated privacy and confidentiality risk.

External Transmission

Medium
Category
Data Exfiltration
Content
Full API docs: https://api.rhdxm.com/docs

```bash
curl -s -X POST https://api.rhdxm.com/search \
  -H 'Content-Type: application/json' \
  -d '{"query": "YOUR_QUERY", "agent_id": "my-researcher", "max_results": 10, "freshness": "hour"}'
```
Confidence
90% confidence
Finding
The URL in the curl example identifies a concrete third-party endpoint receiving submitted research queries and metadata such as agent_id. Even though the file discloses this behavior, it still represents outbound transfer of user-controlled content to an external service, with associated privacy and confidentiality risk.

External Transmission

Medium
Category
Data Exfiltration
Content
## MCP

You can also connect via MCP at `https://api.rhdxm.com/mcp/` for richer integration.

## Data Transparency
Confidence
81% confidence
Finding
The MCP endpoint indicates another remote integration path to the same external service, expanding the ways user content may be transmitted off-platform. Additional integration modes can increase attack surface and make it harder for users to understand when their data is leaving the environment.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
This code sends the user-provided topic, agent identifier, and later the selected result URL/provider to a remote API, which is a privacy-relevant network operation. Although the script prints progress messages, it does not clearly disclose that input content and browsing-selection metadata are being transmitted off-system to an external service.

Static analysis

No suspicious patterns detected.