Back to skill

Security audit

产业链上下游拓客

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report credential exposure, an extra promotional workflow, and a mismatch between its stated prospecting purpose and reported behavior; coverage is partial.

Consider the suspicious verdict before installing. Do not paste a reusable API key into chat; use a local secret-setting method if you choose to proceed. Review whether the reported document conversion and credit-related promotional workflow match what you want, and treat the scan as incomplete because a referenced local path could not be resolved.

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

文档导出可以作为报告生成的辅助步骤,但所提供代码仅包含格式转换命令,没有客户关系数据检索、产业链分析或拓客建议生成逻辑。因此,就所提供代码而言,其实际主要用途与声明用途存在实质差异。

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 251)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')=='商机挖掘' for b in s.get('buddies',[]) if b.get('title')=='产业链上下游拓客'];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 instructs users to paste an API key into the conversation without warning about credential exposure.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

The setup repeatedly asks users to paste an API key into the conversation, unnecessarily exposing a reusable credential to chat history, logging, and any systems with access to those records. Although authentication to Cue is necessary, conversational disclosure is not and could enable unauthorized API usage or credit consumption within the key's permissions.

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 226)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 227)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 skill adds a mandatory referral, purchase, and social-media promotion workflow beyond supply-chain prospecting.

Low
Category
Excessive Agency
Confidence
91% confidence
Finding

The skill mandates a vendor-promotional interaction and suppresses other follow-up questions when credits are low, redirecting the assistant beyond the user's prospecting request. This is a limited workflow-hijacking risk rather than demonstrated fraud or exfiltration: the options include declining, and no purchase or social posting is automatically executed.

Content

No source excerpt is available for this finding.

The mandatory low-credit prompt forces Chinese output without a language choice.

Low
Category
Output Handling
Confidence
88% confidence
Finding

The skill requires the supplied Chinese question and options to be used verbatim, explicitly prohibiting changes to their wording. This fixes the language of that user-facing interaction without user opt-in or a documented locale-specific justification.

Content

No source excerpt is available for this finding.