ClawHub
Back to skill

Security audit

xinjianxue-relation-advisor

Security checks for vulnerabilities and agentic risk

Overview

Ordinary relationship questions can trigger sending personal birth details to an outside service before the workflow asks the user to approve payment.

Before installing, require explicit approval before any external request and confirm the provider's data-retention practices. Reports cost 6 yuan through Alipay. Declining payment stops delivery, but the documented workflow has already sent birth details by then.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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
Findings (6)

L23 lists broad everyday relationship phrases as triggers without requiring an explicit request for 心鉴学 analysis.

Medium
Category
Trigger Abuse
Confidence
97% confidence
Finding

Generic relationship and self-reflection questions can activate a paid, birth-information-based service even when the user only wants ordinary advice. The prescribed workflow immediately collects personal information and calls a service without first confirming that the user wants this analysis method and accepts its price; the payment requirement does not itself establish informed consent to activation or data collection.

Content

No source excerpt is available for this finding.

L40–L41 instruct collection of personal information and use of an external analysis service without a privacy disclosure.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow collects precise birth details, gender, and potentially intimate relationship information, then directs use of an external analysis service without requiring a privacy disclosure or consent checkpoint. This creates a risk of sharing personal information beyond the user's expectations, although the unavailable API reference prevents verification of the actual payload, recipient, or downstream handling.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · references/api.md (reported line 3)May include surrounding context.

md
# 接口契约

- 地址：`https://api.xinjianxue.com/api/xinjianxue/aipay/report`
- 方法：POST，`Content-Type: application/json`
- 单价：6 元/次
- 服务 ID：`API_114161C46CE74BDE`

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · references/payment.md (reported line 8)May include surrounding context.

1. 发起请求

bash
curl -sS -D - -X POST "https://api.xinjianxue.com/api/xinjianxue/aipay/report" \
  -H "Content-Type: application/json" \
  -d '{"birth":"1995-08-04 05:52","place":"浙江杭州","country":"CN","gender":"女"}'

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 · references/payment.md (reported line 8)May include surrounding context.

1. 发起请求

bash
curl -sS -D - -X POST "https://api.xinjianxue.com/api/xinjianxue/aipay/report" \
  -H "Content-Type: application/json" \
  -d '{"birth":"1995-08-04 05:52","place":"浙江杭州","country":"CN","gender":"女"}'

The request workflow sends personal birth details to an external service without a user-facing privacy warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The workflow directs the agent to send birth date and time, birthplace, country, and gender to an external service without first requiring a privacy disclosure or informed authorization. Although this processing supports the skill's stated purpose, that context does not ensure users understand that their personal information leaves the conversation; payment authorization occurs later and does not establish consent to this initial transmission.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.