ClawHub
Back to skill

Security audit

Ruofan Bargain Arena

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow event helper that sends user-provided bargain messages to Ruofan's API, with privacy considerations but no hidden or destructive behavior found.

Before installing, understand that your passphrase, nickname, and bargain messages will be sent to ruffood.com, and the bargain conversation may appear publicly on the event page. Do not include personal or sensitive information in the nickname or messages, and treat the returned session token like a private access token.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to send user-supplied passphrase and nickname to a third-party service, but it does not explicitly warn the user at the point of use that their data will be transmitted off-platform. Because the passphrase may be sensitive or single-use and the session is publicly displayed per the skill text, the lack of clear disclosure creates a real privacy and consent issue.

External Transmission

Medium
Category
Data Exfiltration
Content
用户需要提供暗号和自己的昵称。用以下方式调用 API：

```bash
curl -X POST https://ruffood.com/api/bargain/join \
  -H "Content-Type: application/json" \
  -d '{"passphrase": "用户提供的暗号", "name": "用户昵称"}'
```
Confidence
94% confidence
Finding
The skill performs an external network transmission of user-provided passphrase and nickname to an external domain. In context, this behavior is expected for participating in the bargain event, but it is still a real security/privacy concern because sensitive or single-use user data leaves the platform and the instructions do not clearly establish consent boundaries or data-handling expectations.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
The manifest description, trigger pattern, and operating instructions are entirely Chinese and implicitly require Chinese interaction, but the file does not offer a user language option or explain that the skill is intentionally limited to Chinese users. This can violate language/locale policy when a skill forces a specific language without opt-in.

Static analysis

No suspicious patterns detected.