Back to skill

Security audit

热门赛道与ETF深度投研

Security checks for vulnerabilities and agentic risk

Overview

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.

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 (7)

Description-Behavior Mismatch

High
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

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 309)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
98% confidence
Finding

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.

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 284)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 285)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 skill mandates an unsolicited promotional workflow after successfully delivering analysis.

Low
Category
Excessive Agency
Confidence
90% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Mandatory verbatim Chinese prompts impose an output language without user choice.

Low
Category
Output Handling
Confidence
90% confidence
Finding

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.

Content

No source excerpt is available for this finding.