Back to skill

Security audit

上市公司财报分析

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because it reports that the setup asks users to share an API key in chat, stores it in a local configuration file without restrictive permissions, and includes undisclosed referral and purchase prompts; scan coverage was partial.

Review the reported credential handling and promotional prompts before installing. Consider whether you are comfortable sharing a reusable API key through chat and storing it in a local file without enforced restrictive permissions. The scan was partial: it inspected the single reported Markdown component, but two local path references could not be resolved, so the evidence is incomplete.

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 (6)

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 273)May include surrounding context.

bash
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')=='财报深读' for b in s.get('buddies',[]) if b.get('title')=='上市公司财报分析'];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

The setup workflow requests an API key in chat without warning that this exposes a sensitive credential to the conversation system.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

The setup explicitly asks users to paste an API key into the conversation, exposing a reusable credential to chat retention, logging, and any parties or integrations with conversation access. Authentication is necessary for this service, but transmitting the credential through chat is not.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
91% confidence
Finding

Creating ~/.cue is ordinary application configuration, not evidence of malicious session persistence. However, the same command writes an API key without enforcing restrictive directory or file permissions; with a common umask of 022 and a traversable home directory, other local users could read a newly created credential file.

Content

Scanner excerpt · SKILL.md (reported line 199)May include surrounding context.

md
#   git clone https://gitee.com/sensedeal/cue-skills ~/.cue/cue-skills

# 2. 写入 API Key(在 https://cuecue.cn/api-key?src=clawhub-earnings-analysis 创建后复制)
mkdir -p ~/.cue && echo '{"api_key":"sk..."}' > ~/.cue/config.json

# 3. 验证连通(返回 200 即成功)
curl -sS --max-time 10 "https://cuecue.cn/api/templates" \

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 251)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` |

## 架构说明

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 252)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` |

## 架构说明

The earnings-analysis workflow mandates referral and social-media promotion that is not disclosed in the manifest.

Low
Category
Excessive Agency
Confidence
94% confidence
Finding

The skill mandates unsolicited referral, purchase, and social-sharing prompts as part of an earnings-analysis workflow without disclosing this commercial behavior in its metadata. This redirects the assistant toward promotion outside the user's analytical objective, although actual purchasing and sharing remain user-controlled.

Content

No source excerpt is available for this finding.