Interactive Infographic

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:23 PM UTC
• Version:
  0.1.8

Overview

This skill is a disclosed ContextWeave visualization client that runs local Node scripts and sends the selected request or diagram content to a remote backend.

Install only if you are comfortable sending the text, diagrams, or architecture details you ask it to visualize to https://pptx.chenxitech.site. Avoid including secrets, regulated data, or proprietary material unless you trust that backend, and prefer a scoped ContextWeave API key over unrelated credentials in your environment.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (4)

Context-Inappropriate Capability

Medium

• Confidence: 99% confidence
• Finding: The client loads an API key from the environment but silently falls back to a hardcoded credential embedded in source. Hardcoded secrets are recoverable by anyone with code access and can enable unauthorized use of the upstream service, quota abuse, impersonation of legitimate clients, and difficulty rotating compromised credentials.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: When an input file is provided, the code reads its full contents, extracts request/diagram text, and sends that data to a remote API endpoint. This creates a data exfiltration risk for sensitive local content, and the file contains no user-facing disclosure, consent check, redaction step, or clear indication that local material will leave the machine.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The importCode path reads local diagram content and uploads it to a remote session import endpoint without any warning in this file. Even if the target is expected to be a diagram file, it may still contain proprietary architecture, business logic, or embedded secrets, so silent transmission to a third party is a meaningful confidentiality risk.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The script sends a user-supplied local path to an external ContextWeave client import operation without any user-facing confirmation, warning, or scope preview. In a skill explicitly designed to ingest and visualize complex code and knowledge bases, this increases the chance that users will unknowingly transmit sensitive source code, secrets, or proprietary context to a backend service.

VirusTotal

63/63 vendors flagged this skill as clean.