ClawHub
Back to skill

Security audit

Ifc Data Extraction

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent IFC/BIM data extraction helper, but users should review exports because BIM model data can be sensitive.

Install only if you are comfortable granting filesystem access for IFC files and exports. Before exporting, especially to SQL or shared folders, confirm that the BIM data may be shared and avoid sending building layouts or project metadata to unintended destinations.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill provides bulk export to Excel, CSV, JSON, and SQL without warning that IFC/BIM data may contain sensitive project details such as building layouts, room data, materials, identifiers, and operational metadata. In practice, this can lead users or autonomous agents to persist and disseminate sensitive information to local files or external systems without appropriate review.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill adds SQL export capability beyond simple IFC parsing, enabling extracted BIM/project data to be written to arbitrary databases via a caller-supplied connection string. That expands the data exfiltration surface and can facilitate unintended transfer of sensitive building metadata, especially in agentic environments where outputs may be routed automatically.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The markdown includes a Russian quotation while the rest of the skill is in English, but it does not provide a translation choice, opt-in, or explain a locale-specific requirement. This can violate language/locale policy expectations when users are not given control over language presentation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.