ClawHub
Back to skill

Security audit

粉象网购省钱管家

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this shopping assistant skill suspicious because it reports that users’ requests are sent to an external service without a user-facing privacy notice; one referenced file was only partly analyzed, so the evidence is incomplete.

Consider the privacy concern and incomplete analysis before installing. The scan reports that shopping requests and follow-up answers are sent to an external service without a user-facing notice, and one referenced file was only partly analyzed. The verdict is suspicious, not a claim that the author acted maliciously.

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Tainted flow: 'request' from os.environ.get (line 54, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/fenxiang_mcp.py (reported line 61)May include surrounding context.

python
method="POST",
        )
        try:
            with urllib.request.urlopen(request, timeout=self.timeout, context=self.context) as response:
                body = response.read().decode("utf-8")
                content_type = response.headers.get("Content-Type", "")
        except urllib.error.HTTPError as error:

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 200)May include surrounding context.

md
- `references/tools.md`：8 个工具的入参、关键出参和价格字段

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, mcp, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The workflow sends users’ verbatim shopping requests and follow-up answers to an external service without a user-facing privacy notice.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The workflow explicitly forwards verbatim requests and accumulated clarification answers to an external recommendation service without requiring a user-facing disclosure or data minimization. Shopping requests can contain sensitive health needs, recipient details, or personal circumstances that are unnecessary for finding products; identifying the backend in technical documentation does not adequately inform users of this disclosure.

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 · SKILL.md (reported line 194)May include surrounding context.

python3 scripts/verify.py # 全链路自检：先搜索拿到在售链接，再逐个工具验证

text

- 默认地址 `https://api.fenxianglife.com/njia/mcp`，可用 `FENXIANG_MCP_URL` 或 `--url` 覆盖。
- 当前服务不需要 API Key；如后续恢复鉴权，用 `FENXIANG_MCP_API_KEY` 或 `--api-key-file` 传入，不要写进 Skill 或对话。
- 证书默认严格校验，`--insecure` 只用于内网自签名测试环境。

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 · scripts/fenxiang_mcp.py (reported line 12)May include surrounding context.

python
python3 fenxiang_mcp.py prompts/list

环境变量：
  FENXIANG_MCP_URL          默认 https://api.fenxianglife.com/njia/mcp
  FENXIANG_MCP_API_KEY      可选；当前服务不需要鉴权

TLS：默认严格校验证书；仅内网自签名测试环境可显式加 --insecure。

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/tools.md (reported line 5)May include surrounding context.

md
## 连接

- 生产：`https://api.fenxianglife.com/njia/mcp`
- 协议：MCP Streamable HTTP（无状态，`POST /mcp`），JSON-RPC 2.0；`initialize` 返回 `instructions`（选工具与回答规则），`prompts/list` 有 4 个常用提示词
- 鉴权：当前服务不需要 API Key；如后续恢复，支持 `Authorization: Bearer <API Key>` 或 `X-Api-Key: <API Key>`
- 请求头：`Content-Type: application/json`，`Accept: application/json, text/event-stream`

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 · scripts/fenxiang_mcp.py (reported line 27)May include surrounding context.

python
import urllib.error
import urllib.request

DEFAULT_URL = "https://api.fenxianglife.com/njia/mcp"
TOOLS = (
    "buy_advice", "batch_analyze", "compare_by_name", "recommend_goods",
    "goods_search", "history_price", "compare_price", "saving_plan",