ClawHub
Back to skill

Security audit

Ifc Data Extraction

Security checks across malware telemetry and agentic risk

Overview

This skill is mostly a local IFC extraction helper, but its database export example can write and replace SQL tables through an unrestricted connection string despite saying no network access is required.

Install only if you are comfortable with the agent exporting IFC model data. Prefer local CSV, Excel, JSON, pandas, or local SQLite outputs unless you explicitly intend to provide database credentials, and avoid production or remote database connection strings unless replacing the target tables is acceptable.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
86% confidence
Finding
This markdown file includes examples for writing extracted model data to Excel, CSV, JSON, and SQL tables, including overwriting database tables with `if_exists='replace'`, but it does not warn users that these actions can persist sensitive building/model data or overwrite existing outputs. For markdown files, SQP-2 applies when the skill description omits warnings about behaviours that could affect user data, privacy, or system integrity.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The quoted description is presented in Russian while the rest of the skill is in English, and there is no indication that users can choose their language or that the skill is intentionally region-specific. The rule covers natural-language locale policy issues when a specific language is imposed without opt-in or justification.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.