Mineru Extract

• Outcome: Review
• Latest audit: Sep 16, 2026 · 9:53 AM UTC
• Version: 0.1.0

Overview

The skill is mostly purpose-aligned, but it needs review because it recommends an unsafe system-wide Python install and sends user documents to external MinerU/OSS services.

Review before installing. Use a virtual environment instead of the documented system-wide pip command, pin dependencies where possible, and avoid uploading confidential, regulated, or proprietary documents to MinerU unless you are comfortable with the third-party processing path.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

• Location: SKILL.md:12

Finding

Unpinned System-Wide Python Dependency Installation

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, lines 12-16
Vulnerability Type: Unsafe third-party dependency installation
Risk Level: Medium

Vulnerable Code

markdown

## 安装

首次使用时，安装依赖：

```bash
pip3 install --break-system-packages requests python-dotenv

text

### Technical Analysis

The installation command retrieves `requests` and `python-dotenv` from the configured Python package index without pinning reviewed versions, verifying cryptographic hashes, or using a lock file. Consequently, the installed artifacts can change between executions even though the audited skill content remains unchanged.

The command also uses `--break-system-packages`, which bypasses Python's externally managed environment protection. This permits pip to modify the host's system-managed Python environment and can overwrite or conflict with operating-system packages.

Exploitation requires the configured package source or a selected dependency release to become malicious or otherwise untrusted. No evidence in the audited project indicates that either named package is currently malicious; the finding concerns the unsafe installation mechanism and resulting supply-chain exposure.

### Attack Path

1. A user or agent follows the first-use installation instructions.
2. The command connects to the configured Python package index and resolves the latest acceptable dependency versions.
3. An attacker who has compromised the package source, a dependency release, or the relevant package-distribution path supplies a malicious artifact.
4. Pip downloads and installs that artifact without checking a project-defined version or hash.
5. Package installation logic executes with the privileges of the invoking account.
6. Because `--break-system-packages` permits changes to the system Python environment, malicious or incompatible components can affect other Python applications that use the same environment.

### Impact Assessment

A malicious dependency artifact could ex
...[truncated 594 chars]

Remediation

View remediation

Remediation Suggestions

1. Remove --break-system-packages and install dependencies in a dedicated virtual environment:

bash

python3 -m venv .venv
. .venv/bin/activate
python3 -m pip install --require-hashes -r requirements.txt

2. Pin every direct and transitive dependency to a reviewed version in requirements.txt.
3. Record SHA-256 hashes for every permitted distribution and enforce them with --require-hashes.
4. Generate and review a dependency lock file using a tool such as pip-tools.
5. Use a trusted, explicitly configured package index and secure transport.
6. Periodically scan locked dependencies for known vulnerabilities and review updates before changing pinned versions.
7. Document that installation must not be performed as root or in the operating system's managed Python environment.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (5)

Credential Access

High

• Category: Privilege Escalation
• Confidence: 60% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

在项目目录创建 .env 文件：

bash

# .env
MINERU_API_KEY="your-api-key-here"

Credential Access

High

• Category: Privilege Escalation
• Confidence: 60% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

在项目目录创建 .env 文件：

bash

# .env
MINERU_API_KEY="your-api-key-here"

Credential Access

High

• Category: Privilege Escalation
• Confidence: 60% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

在项目目录创建 .env 文件：

bash

# .env
MINERU_API_KEY="your-api-key-here"

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

The skill instructs users to upload local documents/images to MinerU and intermediate OSS endpoints but does not warn that file contents leave the local environment and are sent to third-party services. This creates a real privacy and data-handling risk because users may unknowingly transmit sensitive documents, credentials, personal data, or proprietary materials to external infrastructure.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

The skill metadata and instructions are written to operate in Chinese and do not indicate that users may choose another language or locale. This can violate language/locale policy when a skill implicitly enforces a specific language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.