ClawHub
Back to skill

Security audit

F-AI 金融数据

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly does what it claims, but its installer can write outside the intended skills folder and its install command runs an unpinned npm package.

Review this before installing. Use a pinned, trusted package version if available, and avoid passing any skill ID other than the documented finloop-mktdata-skill value. Treat the API calls as external requests to Finloop's UAT service and do not include confidential portfolio, account, or personal data unless you trust that service.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:23
Finding

Unpinned npm Package Execution Through npx

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
lib/install.js:42
Finding

Path Traversal in Skill Installation Can Escape the Intended Directories

Content
View full analysis
{ rl.question('', (answer) => { rl.close(); if (answer.toLowerCase() === 'y' || answer.toLowerCase() === 'yes') { fs.rmSync(targetSkillPath, { recursive: true, force: true }); copyDirectory(skillPath, targetSkillPath); console.log(`\n✅ Skill "${skillName}" 安装成功!`); console.log(` 位置: ${targetSkillPath}`); resolve(); } else { console.log('❌ 安装已取消'); reject(new Error('用户取消安装')); } }); }); } else { copyDirectory(skillPath, targetSkillPath); console.log(`\n✅ Skill "${skillName}" 安装成功!`); console.lo ...[truncated 2410 chars]
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (12)

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

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 · .agents/skills/finloop-mktdata-skill/SKILL.md (reported line 112)May include surrounding context.

md
## 通用注意事项

1. **必须直接使用 HTTP 请求**：✅ 直接使用 fetch、axios、curl 调用；❌ 禁止创建封装函数或 JS/TS 文件。
2. **Base URL**：`https://papi-uat.finloopg.com/flp-mktdata-hub`（UAT）；生产以实际为准。
3. **错误处理**：检查 HTTP 状态码和响应体中的错误信息。
4. **调用示例**：

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 · .agents/skills/finloop-mktdata-skill/SKILL.md (reported line 116)May include surrounding context.

md
2. **Base URL**：`https://papi-uat.finloopg.com/flp-mktdata-hub`（UAT）；生产以实际为准。
3. **错误处理**：检查 HTTP 状态码和响应体中的错误信息。
4. **调用示例**：
   - ✅ `fetch('https://papi-uat.finloopg.com/flp-mktdata-hub/v1/stock/quote', { method: 'POST', headers: { 'Content-Type': 'application/json' }, body: JSON.stringify({ code: '00700.HK' }) })`
   - ✅ `curl -X POST 'https://papi-uat.finloopg.com/flp-mktdata-hub/v1/stock/quote' -H 'Content-Type: application/json' -d '{"code":"00700.HK"}'`
   - ❌ 创建 `api/mktdata.ts` 等封装文件并 import 调用。

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 · .agents/skills/finloop-mktdata-skill/references/REFERENCE.md (reported line 94)May include surrounding context.

bash
# 股票实时
curl -X POST 'https://papi-uat.finloopg.com/flp-mktdata-hub/v1/stock/quote' \
  -H 'Content-Type: application/json' -d '{"code":"00700.HK"}'

# 股票历史

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains user-facing natural-language instructions entirely in Chinese, including installation steps and usage guidance. Under the policy rule for language/locale constraints, forcing a single language without offering user choice can be a natural-language policy violation when no justification or opt-in is provided.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The installation command uses npx finloop-mktdata-skills without pinning an exact package version, so consumers may execute whatever code is currently published under that package name. This creates a supply-chain risk where a compromised publisher account, malicious new release, or typosquatted replacement could lead to arbitrary code execution during install.

Content

No source excerpt is available for this finding.

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 · SKILL.md (reported line 112)May include surrounding context.

md
## 通用注意事项

1. **必须直接使用 HTTP 请求**：✅ 直接使用 fetch、axios、curl 调用；❌ 禁止创建封装函数或 JS/TS 文件。
2. **Base URL**：`https://papi-uat.finloopg.com/flp-mktdata-hub`（UAT）；生产以实际为准。
3. **错误处理**：检查 HTTP 状态码和响应体中的错误信息。
4. **调用示例**：

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 · SKILL.md (reported line 116)May include surrounding context.

md
2. **Base URL**：`https://papi-uat.finloopg.com/flp-mktdata-hub`（UAT）；生产以实际为准。
3. **错误处理**：检查 HTTP 状态码和响应体中的错误信息。
4. **调用示例**：
   - ✅ `fetch('https://papi-uat.finloopg.com/flp-mktdata-hub/v1/stock/quote', { method: 'POST', headers: { 'Content-Type': 'application/json' }, body: JSON.stringify({ code: '00700.HK' }) })`
   - ✅ `curl -X POST 'https://papi-uat.finloopg.com/flp-mktdata-hub/v1/stock/quote' -H 'Content-Type: application/json' -d '{"code":"00700.HK"}'`
   - ❌ 创建 `api/mktdata.ts` 等封装文件并 import 调用。

Rp1

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding

The script advertises installation via npx finloop-news-skills without pinning a specific version, which causes users to execute whatever version is current on the registry at install time. If the package is later compromised, typosquatted, or a malicious version is published, consumers may execute unreviewed code unexpectedly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The user-facing help text and error guidance are entirely in Chinese, which imposes a specific language on all users of this CLI. The file does not provide any option, fallback, or documented justification for this locale restriction, so it appears to violate the language/locale choice policy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code presents comments, status messages, errors, and the overwrite confirmation prompt entirely in Chinese, including the interactive installation flow. Because there is no user opt-in or locale selection, the skill effectively enforces a specific language, which matches the natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The script's comments, prompts, and status messages are all in Chinese, including the confirmation prompt at L20. This imposes a specific language on all users without opt-in or justification, which matches the natural-language locale policy violation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.