Security audit

供应商档案整理技能

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent supplier-document purpose, but its instructions under-scope sensitive data handling and include a shell-command workflow that could be unsafe with supplier-controlled input.

Review before installing. Use it only on supplier documents you are authorized to process, keep generated files in an access-controlled location, redact unnecessary contact or business-sensitive fields before sharing, pin dependencies in a virtual environment, and do not build shell commands by interpolating extracted supplier data.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:54
Finding: Shell Command Injection Through Untrusted Supplier Data
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:7
Finding: Unpinned Third-Party Python Dependency
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill is designed to process supplier files that may contain personal contact details and sensitive business information, yet it provides no privacy, retention, access control, or redaction guidance. In practice, this can lead to unnecessary exposure of confidential supplier data in generated Markdown, Word/PDF outputs, SVG labels, or local storage paths, especially when documents are shared or retained without safeguards.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: L227 将该技能描述为“纯文档/脚本技能，无外部依赖风险”，但前文多处明确说明会调用 Python 脚本生成 SVG/Word 文档并保存到当前目录或 assets 路径（如 L55-L63、L74-L80、L214-L215）。这不是单纯的只读文档处理，因此该评价性说明与技能实际行为存在直接矛盾。
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.