Back to skill

Security audit

大类资产配置月报

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because it reports that the skill's actual behavior does not match its promised asset-allocation reporting purpose and flags unsafe API-key handling; the scan is partial.

The verdict is suspicious, with high overall confidence, and Skillspector recommends not installing. Consider whether the skill's reported repository setup and promotional workflow fit your needs, and do not paste API secrets into chat. Coverage is incomplete: the scan inspected the listed Markdown component but could not resolve a referenced local path, and its analyzer reports a partial result.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
Findings (8)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The code performs Git repository synchronization and local filesystem changes. It contains no economic-data retrieval, allocation analysis, or report generation. Repository setup could support the declared workflow, but the supplied chunk provides only that setup and no connection to the promised financial-reporting behavior. There is no evidence here of executing downloaded code or exfiltrating data.

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 230)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')=='大类资产配置月报'];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 instructions request an API key in chat without warning about credential exposure.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

The onboarding instructions explicitly ask users to paste an API secret into the conversation, exposing it to chat history and potentially model-provider, client, or diagnostic logging. Authentication is necessary for this service, but transmitting the secret through ordinary chat is not; exposure could enable unauthorized API usage and credit consumption.

Content

No source excerpt is available for this finding.

Onboarding instructions solicit an API secret in the conversation while claiming the agent cannot view it.

Medium
Category
Data Exfiltration
Confidence
99% confidence
Finding

The claim that the agent cannot view the key conflicts with instructions to send it to the agent and have the agent write it into configuration. This misleading assurance can encourage unsafe disclosure; it is the same underlying credential-handling flaw identified by SQP-2, not an independent exposure path.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The skill requires the Chinese-language question and options to be used verbatim, expressly prohibiting changes. This mandates a particular response language without user opt-in or a documented justification for overriding the user's language.

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 207)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 208)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 report-generation skill mandates an additional referral, purchase, and social-sharing promotion workflow.

Low
Category
Excessive Agency
Confidence
94% confidence
Finding

The skill mandates referral, purchase, and social-sharing prompts and gives them priority over other follow-up questions, introducing commercial steering beyond report generation. This is a low-impact workflow-integrity issue rather than demonstrated fraud or automatic spending: the user can decline, and the text does not itself execute a purchase or publish a report.

Content

No source excerpt is available for this finding.