Description-Behavior Mismatch
- Category
- MCP Tool Poisoning
- Confidence
- 99% confidence
- Finding
文档导出可以作为分析报告的辅助实现细节,本身不应被视为违规能力;但当前提供的代码仅执行 Markdown 到 Word/PDF 的转换,没有任何与所声明金融分析目的相符的逻辑。因此,就该代码块所展示的实际主要用途而言,与声明存在实质性不匹配。
- Content
Security audit
Security checks for vulnerabilities and agentic risk
The verdict is suspicious because scanners report that the skill asks users to share an API key in chat, fetches and runs remote content, and includes behavior that does not match its stated ETF research purpose; scan coverage is partial.
Consider the credential exposure and remote-content execution concerns before installing, along with the promotional prompts and purpose mismatch. The scan is partial: it reports one unresolved local path-like reference, so the evidence does not establish that all referenced behavior was reviewed. The verdict is suspicious, not a claim that the author is malicious.
文档导出可以作为分析报告的辅助实现细节,本身不应被视为违规能力;但当前提供的代码仅执行 Markdown 到 Word/PDF 的转换,没有任何与所声明金融分析目的相符的逻辑。因此,就该代码块所展示的实际主要用途而言,与声明存在实质性不匹配。
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
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 explicitly instructs users to paste an API key into the agent conversation, exposing a usable credential to chat history, logging, and any systems with access to that conversation. Authentication to Cue is legitimate, but collecting the secret through ordinary chat is unnecessary and could enable unauthorized API use or credit consumption if disclosed.
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
| 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` |
---
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
| 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` |
---
When credits fall below 100, the skill mandates promotional prompts and forbids other follow-up questions in that response, allowing a vendor's commercial workflow to displace the user's research workflow. This is a limited agent-behavior hijack rather than evidence of credential theft or automatic purchasing; the balance condition and explicit decline option reduce its impact.
The low-balance workflow requires the question and options to be used verbatim, explicitly prohibiting changes to their Chinese wording. This forces Chinese output without offering a language choice or allowing translation to the user's language; the restriction is not justified by the ETF market scope.