Back to skill

Security audit

疑难法律实操案例库

Security checks for vulnerabilities and agentic risk

Overview

The skill is marked suspicious because scanners report behavior that does not match its legal-research purpose and instructions to share an API key in chat; they did not establish malicious intent.

Consider avoiding installation until the API-key handling and the mismatch between the stated legal-research purpose and the reported extra functions are clarified. Do not paste a secret key into chat. The scan is marked partial because a referenced local path was missing, so some evidence is incomplete; the scanners did not establish malicious intent.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Findings (11)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

所提供代码没有执行法律资料检索、访问裁判文书或监管问答来源,也没有进行案例分析。文档导出可以作为法律检索工具的辅助功能,但该代码块仅包含独立的格式转换命令,未体现与所声明法律功能的关联,因此其实际主要行为与描述不符。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied chunk is an operational diagnostic and account-status script. It does not accept a legal dispute, search judgments or regulatory materials, retrieve cases, or analyze legal outcomes. Authentication and availability checks could support a larger legal-search workflow, but this chunk contains only those checks and an undeclared billing lookup. The credential is sent to the Cue service as an authentication token; the code alone does not establish malicious credential exfiltration.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied chunk performs only local configuration writes; it does not search, retrieve, or analyze legal materials. Configuration can be a supporting implementation detail, but nothing supplied connects this particular configuration to the declared service. The overwrite could also replace an existing API key with a placeholder. No network access or credential exfiltration is shown.

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 284)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 if s.get('secondary_category')=='法律合规' for b in s.get('buddies',[]) if b.get('title')=='疑难法律实操案例库'];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')

API-key onboarding requests disclosure through chat without a credential-exposure warning.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The onboarding instructions repeatedly require users to paste a bearer API key into the conversation, unnecessarily exposing it to chat retention, transcripts, and systems processing those messages. The sample configuration write also sets no explicit restrictive permissions, so local exposure depends on the existing file permissions and process umask.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 206)May include surrounding context.

Cue API Key:在 cuecue.cn 注册后免费创建,新账号送 500 积分 + 每天 10 积分。点击「创建 API Key」,生成 API Key 后一定要点击「复制」并粘贴发送给您正在使用的智能体。写入 ~/.cue/config.json:

bash
mkdir -p ~/.cue
echo '{"api_key": "sk你的key"}' > ~/.cue/config.json

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 255)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 256)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` |

---

Standalone topic triggers can activate case-law research without research intent.

Low
Category
Trigger Abuse
Confidence
87% confidence
Finding

Triggers such as “离婚” (divorce), “继承” (inheritance), and “交通事故” (traffic accident) identify topics rather than requests for legal-case research. They can occur in emotional-support conversations, programming discussions, or emergency requests, and the skill provides no exclusion conditions for these uses.

Content

No source excerpt is available for this finding.

The skill mandates Chinese-language reports without offering a language choice.

Low
Category
Output Handling
Confidence
88% confidence
Finding

The output specification explicitly requires a Chinese report, and lines 402–403 repeat that requirement without offering user opt-in or another language. Although the research covers domestic Chinese cases, the file does not explain why the report itself must be Chinese regardless of the user's preferred language.

Content

No source excerpt is available for this finding.

The legal-research skill mandates an unrelated referral and social-media promotion workflow.

Low
Category
Excessive Agency
Confidence
94% confidence
Finding

The skill requires a promotional workflow and forbids other follow-up questions until it has been presented, allowing vendor marketing instructions to displace the user's legal-research priorities. The social-sharing option also carries a report identifier, creating a potential privacy concern for sensitive legal matters, although the text does not itself automatically publish a report.

Content

No source excerpt is available for this finding.