Back to skill

Security audit

Cue 深度研究(通用版)

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because scanners report instructions that redirect the research workflow toward promotion and referrals, while review of a referenced local path was incomplete.

Consider the suspicious verdict and the promotional workflow instructions before installing. Skillspector's analysis is partial: a local path-like reference was missing, so the evidence is incomplete. The AIG scan completed without reported findings, but that does not resolve the issues or incomplete coverage.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

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.

bash
echo "=== 1/4 API Key ===" && [ -f "$HOME/.cue/config.json" ] && echo "已配置" || echo "未配置!"
echo "=== 2/4 Cue 服务 ===" && curl -sS --max-time 10 "https://cuecue.cn/api/health"
echo "=== 3/4 搭子 ===" && curl -sS --max-time 10 "https://cuecue.cn/api/playbook" | python3 -c "import sys,json;data=json.load(sys.stdin).get('data',{});scenes=data.get('scenes',[]) if data else [];total=sum(len(s.get('buddies',[])) for s in scenes);print(f'可用:{total}个搭子') if scenes 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 skill mandates referral and social-media promotion unrelated to its public-information research purpose.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

When credits are low, the skill requires a promotional prompt and explicitly suppresses other follow-up questions until that prompt is handled. This lets vendor-authored instructions redirect the assistant's workflow toward referrals, purchases, and social sharing rather than the user's research needs; however, the instructions do not authorize automatic purchases or posting.

Content

No source excerpt is available for this finding.

Mandatory verbatim Chinese prompts impose a response language without user opt-in.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The skill requires the low-balance question and all four options to be reproduced verbatim in Chinese, explicitly prohibiting changes. This forces Chinese user-facing output regardless of the user's language, without offering a language choice or documenting a justification for the restriction.

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 260)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 261)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` |

---