Back to skill

Security audit

盘后超级助理

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report behavior beyond its A-share analysis purpose, including credential and installation risks; Skillspector coverage was partial, so the evidence is incomplete.

Consider the suspicious verdict and the incomplete Skillspector analysis before installing. In particular, review whether you are comfortable sharing an API key in chat, letting the skill install or update and run code from a remote repository, and setting up recurring runs; avoid sharing credentials in conversation.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (12)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied chunk only converts an existing local document into two output formats. It contains no market-data retrieval, market analysis, or other behavior connecting the conversion to the declared financial-review workflow. Although document conversion could support report delivery, the supplied code provides no such context and has a materially different apparent primary purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied chunk contains no market-data retrieval or market-analysis logic. Authentication, service-health checks, and assistant discovery could support the declared service and are not inherently mismatches. However, this chunk's actual purpose is a diagnostic checklist that also accesses private billing and credit information, which is outside the declared market-analysis scope. The mismatch does not establish malicious credential theft: the key is used to authenticate requests to the Cue service.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

Installing a runner is a legitimate dependency, so the description mismatch alone is not a vulnerability. However, the skill automatically clones or updates an unpinned remote repository, including a fallback mirror, and subsequently executes its Python code; a compromised upstream or mirror could therefore run arbitrary code with the user's permissions and access locally available credentials.

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 410)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')=='财富投顾' for b in s.get('buddies',[]) if b.get('title')=='盘后超级助理'];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 repeatedly instructs users to paste a live API key into the conversation rather than configure it through a secret-entry mechanism. This unnecessarily exposes the credential to conversation storage, model processing, and potentially transcript exports or logging, allowing anyone who obtains it to use whatever account capabilities the key grants.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% 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 241)May include surrounding context.

md
| 环境 | 配置方式 |
|------|---------|
| Claude Code | 用 `CronCreate`,cron 表达式 `10 17 * * 1-5`(自定义时间按用户所选取 分 时 日 月 周) |
| macOS | 建 `~/Library/LaunchAgents/com.cue.after-market.plist`,`StartCalendarInterval` 设 `Weekday` 1–5、`Hour` 17、`Minute` 10,再 `launchctl load` |
| Linux | `crontab -e` 追加 `10 17 * * 1-5 <上面的命令>` |

配完必须回报三件事:**触发时间、输出目录、如何关掉**(Claude Code 删任务 / `launchctl unload` / `crontab -e` 删除对应行)。

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% 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 241)May include surrounding context.

md
| 环境 | 配置方式 |
|------|---------|
| Claude Code | 用 `CronCreate`,cron 表达式 `10 17 * * 1-5`(自定义时间按用户所选取 分 时 日 月 周) |
| macOS | 建 `~/Library/LaunchAgents/com.cue.after-market.plist`,`StartCalendarInterval` 设 `Weekday` 1–5、`Hour` 17、`Minute` 10,再 `launchctl load` |
| Linux | `crontab -e` 追加 `10 17 * * 1-5 <上面的命令>` |

配完必须回报三件事:**触发时间、输出目录、如何关掉**(Claude Code 删任务 / `launchctl unload` / `crontab -e` 删除对应行)。

Session Persistence

Medium
Category
Rogue Agent
Confidence
85% 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 242)May include surrounding context.

md
|------|---------|
| Claude Code | 用 `CronCreate`,cron 表达式 `10 17 * * 1-5`(自定义时间按用户所选取 分 时 日 月 周) |
| macOS | 建 `~/Library/LaunchAgents/com.cue.after-market.plist`,`StartCalendarInterval` 设 `Weekday` 1–5、`Hour` 17、`Minute` 10,再 `launchctl load` |
| Linux | `crontab -e` 追加 `10 17 * * 1-5 <上面的命令>` |

配完必须回报三件事:**触发时间、输出目录、如何关掉**(Claude Code 删任务 / `launchctl unload` / `crontab -e` 删除对应行)。

Session Persistence

Medium
Category
Rogue Agent
Confidence
85% 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 244)May include surrounding context.

md
| macOS | 建 `~/Library/LaunchAgents/com.cue.after-market.plist`,`StartCalendarInterval` 设 `Weekday` 1–5、`Hour` 17、`Minute` 10,再 `launchctl load` |
| Linux | `crontab -e` 追加 `10 17 * * 1-5 <上面的命令>` |

配完必须回报三件事:**触发时间、输出目录、如何关掉**(Claude Code 删任务 / `launchctl unload` / `crontab -e` 删除对应行)。

### 必须提前告知的两个坑

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 326)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` |

## 可视化看板(输出增强)

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 327)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` |

## 可视化看板(输出增强)

The health check reads the API key despite documentation stating that the agent has no authority to view it.

Low
Category
Excessive Agency
Confidence
94% confidence
Finding

L274 and L396 explicitly state that the agent cannot view the user's API key. However, L407 reads the plaintext key from configuration or the environment into a shell variable, and L414 reads it again for authenticated requests. Authentication is appropriate for this skill, but the stated credential-access restriction contradicts the implementation.

Content

No source excerpt is available for this finding.