Electrical Schematic Review

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 10:46 AM UTC
• Version: 1.0.0

Overview

This appears to be a straightforward electrical schematic review skill with a local report-generation script, with ordinary dependency and localization cautions.

Before installing, use a virtual environment and consider pinning the Python package versions. Verify the checklist you want the agent to use, because the referenced references/checklist.md file is not included, and expect Chinese-language report labels unless you adapt the script or ask the agent for another language.

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:147

Finding

Unpinned Third-Party Dependency Installation

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, line 147
Vulnerability Type: Supply-chain exposure caused by unpinned dependencies
Risk Level: Medium

Complete Code Snippet:

bash

pip install PyMuPDF openpyxl reportlab

Technical Analysis

The documented installation command installs three third-party packages without version constraints, integrity hashes, a lock file, or an explicitly trusted package index. Consequently, package resolution depends on the mutable state of the configured Python package index when installation occurs.

This does not prove that any named dependency is currently malicious. However, it creates supply-chain exposure: a compromised upstream release, compromised package-index account, or attacker-controlled index configuration could cause users to install code that was not reviewed as part of this Skill. Python packages may execute build or installation logic, and their imported modules execute in the context of the user running the Skill.

Attack Path

1. A user follows the dependency-installation instruction in SKILL.md.
2. pip resolves the latest compatible package releases through the user's configured package indexes.
3. An attacker compromises an upstream release or influences resolution through a hostile or misconfigured package index.
4. pip downloads and installs the attacker-controlled package or release because no version or artifact hash is enforced.
5. Malicious code executes during package installation, package build, or subsequent import by the document-processing workflow.

Impact Assessment

Exploited dependency code would normally run with the privileges of the user invoking pip or the report-generation workflow. It could access files and environment variables available to that user, alter generated reports, process sensitive schematic or review data, establish network connections, or modify user-writable resources.

...[truncated 339 chars]

Remediation

View remediation

Remediation Suggestions

1. Replace the free-form installation command with a reviewed, version-pinned dependency manifest.

2. Pin exact versions rather than using open-ended or broad version ranges.

3. Record cryptographic hashes for every approved artifact and install with hash verification, for example:

   bash

   python -m pip install --require-hashes -r requirements.txt
   

4. Generate and review a lock file that includes transitive dependencies.

5. Explicitly use a trusted package index and disable unintended supplemental indexes where operationally appropriate.

6. Install dependencies inside an isolated virtual environment under a non-privileged account.

7. Periodically scan and update pinned dependencies through a controlled review process rather than resolving mutable latest versions at installation time.

8. Document supported Python and dependency versions so users can reproduce the reviewed environment.

SkillSpector

Vulnerability Patterns

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

Findings (3)

Hidden Instructions

High

• Category: Prompt Injection
• Confidence: 60% confidence

Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md

---
name: electrical-schematic-review
description: "Review electrical schematics from EPLAN and similar CAD tools against standardized checklists"
tags: [domain-specific, electrical, visual, template-based, file-based]

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill title and operational description are written entirely in Chinese, and the document gives no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

This code file includes natural-language strings and documentation entirely in Chinese, including the module docstring and CLI description. Under the policy rule, forcing a specific language without user opt-in is a locale/language policy concern unless the constraint is explicitly justified.

Content

No source excerpt is available for this finding.