Security audit

Drawing Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward drawing-analysis helper that reads user-provided construction documents and reports extracted data, with some normal privacy and dependency cautions.

Install in an isolated Python environment when possible, consider pinning `pdfplumber`, and review drawings and generated reports for sensitive project names, identifiers, design details, or internal notes before sharing outputs.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:451
Finding: Unpinned Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill extracts title block fields, annotations, schedules, and other text from construction drawings, then surfaces that content in generated reports. Because drawings commonly contain sensitive project metadata, internal identifiers, and design details, omitting a warning can cause users to unintentionally process and expose sensitive information in downstream outputs or logs.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.