Back to skill

Security audit

个人背调底稿

Security checks for vulnerabilities and agentic risk

Overview

The background-check workflow is coherent, but its setup unnecessarily exposes your API key by requiring you to paste it into chat.

Review before installing. Configure your API key privately through a protected local configuration or environment variable instead of pasting it into chat; replace a key already shared there. Review downloaded runner updates, understand that research queries go to Cue, and check report-link visibility before sharing background-check material.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Document conversion could support delivery of a due-diligence report, but the supplied chunk only converts an existing Markdown file. It contains none of the substantive investigative or analytical behavior central to the declared purpose. The mismatch concerns the materially different implemented purpose, not document conversion as an undeclared supporting detail.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding

The supplied code performs repository installation and maintenance only. It contains no business-record retrieval, judicial-history analysis, control-network mapping, or report generation. Although repository setup could support a larger Cue workflow, the supplied chunk does not establish that connection or implement the declared purpose. No execution of downloaded repository contents is shown.

Content

No source excerpt is available for this finding.

The setup instructions direct the agent to solicit the user's API key in conversation.

Medium
Category
Data Exfiltration
Confidence
99% confidence
Finding

The skill repeatedly instructs users to paste their API key into the agent conversation, exposing a reusable credential to chat history, logging, and any systems or people with access to those records. The key is legitimately needed for Cue authentication, but conversational collection unnecessarily expands exposure and could enable unauthorized API use or consumption of account credits.

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 160)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 161)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` |

---

Static analysis

No suspicious patterns detected.