Back to skill

Security audit

热门赛道与ETF深度投研

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because scanners report requests to share an API key in chat, promotional prompts, and possible mismatches between its stated investment purpose and demonstrated actions; coverage is partial.

Consider the suspicious verdict before installing. In particular, avoid pasting a reusable API key into chat, and consider whether the promotional prompts and reported differences between the advertised purpose and some demonstrated actions are acceptable. The scan covered one Markdown file but was marked partial because a referenced local path could not be resolved, so the evidence is incomplete.

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
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The code contains only two document-conversion commands. It does not retrieve financial data, compare ETFs, examine holdings, assess valuations, or produce investment analysis. Document export could support a broader reporting workflow, but no such analytical workflow is present in the supplied chunk; its sole demonstrated purpose materially differs from the declared purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

认证、服务检查和积分查询可以作为投研功能的辅助步骤,本身不构成异常能力。但所提供代码的全部行为止于这些前置检查:它只检查名为“热门赛道/ETF深度投研”的搭子是否存在,并未调用该搭子开展分析,也未获取或处理投资研究数据。因此,仅就所提供代码而言,其实际功能是可用性与账户状态诊断,与声明的深度投研功能存在实质差距。没有证据表明它向无关第三方泄露凭据。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied chunk only manages a remote skill repository; it contains no sector research, ETF comparison, holdings analysis, or valuation functionality. Repository setup could support a larger implementation, but no connection to an analysis workflow is shown here. On the supplied evidence, its primary behavior is an undeclared installation/update operation. The chunk does not explicitly execute the downloaded content.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 311)May include surrounding context.

md
CUE_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.cue/config.json'))['api_key'])" 2>/dev/null || echo "$CUE_API_KEY")
echo "=== 1/4 API Key ===" && [ -n "$CUE_KEY" ] && echo "已配置" || echo "未配置!"
echo "=== 2/4 Cue 服务 ===" && curl -sS --max-time 10 "https://cuecue.cn/api/health" -H "Authorization: Bearer $CUE_KEY"
echo "=== 3/4 搭子 ===" && curl -sS --max-time 10 "https://cuecue.cn/api/playbook" -H "Authorization: Bearer $CUE_KEY" | python3 -c "import sys,json;scenes=json.load(sys.stdin).get('data',{}).get('scenes',[]);buddy=[b for s in scenes for b in s.get('buddies',[]) if b.get('title')=='热门赛道/ETF深度投研'];print(f'可用:{len(buddy)}个') if buddy else print('暂不可用')"
echo "=== 4/4 剩余积分 ===" && python3 -c "
import json, urllib.request, os
p = os.path.expanduser('~/.cue/config.json')

The setup workflow requests an API key in chat without warning about credential exposure.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

The setup instructions repeatedly ask users to paste an API key into the conversation, exposing a reusable credential to chat history, logging, and any systems that process the conversation. The statement that the agent cannot view the key does not protect a secret subsequently supplied directly to that agent; exposure could enable unauthorized API use and credit consumption.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 286)May include surrounding context.

md
| 目标格式 | 依赖 | macOS | Ubuntu |
|----------|------|-------|--------|
| Word (.docx) | pandoc | `brew install pandoc` | `sudo apt install pandoc` |
| PDF (.pdf) | pandoc + LaTeX | `brew install --cask basictex` | `sudo apt install texlive-xetex` |

---

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 287)May include surrounding context.

md
| 目标格式 | 依赖 | macOS | Ubuntu |
|----------|------|-------|--------|
| Word (.docx) | pandoc | `brew install pandoc` | `sudo apt install pandoc` |
| PDF (.pdf) | pandoc + LaTeX | `brew install --cask basictex` | `sudo apt install texlive-xetex` |

---

The research workflow mandates referral, purchase, and social-promotion prompts beyond the manifest's ETF-analysis purpose.

Low
Category
Excessive Agency
Confidence
94% confidence
Finding

The skill mandates referral, purchase, and social-promotion prompts and gives them priority over other follow-up questions. Although related to service billing, these requirements redirect the assistant toward provider marketing without a user request; they do not themselves authorize a payment or publish a report.

Content

No source excerpt is available for this finding.