china-poster-studio

• Outcome: Pass
• Latest audit: May 29, 2026, 8:29 PM
• Version:
  1.1.1

Overview

This is a documentation-only poster-generation skill with optional URL fetching, and I found no hidden execution, credential use, persistence, or destructive behavior.

Safe for normal poster-generation use. Prefer pasting article text directly when privacy matters, and do not provide private, intranet, authenticated, or token-bearing URLs. Install Pillow and any fonts only from trusted sources if using local generation.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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 (2)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The skill can be triggered by very broad natural-language inputs such as pasted text, short descriptions, or URLs, which overlap heavily with normal user conversation. This increases the chance of accidental invocation, causing unexpected content processing or external fetch behavior without clear user intent.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The documentation states that the agent may fetch user-provided URLs to generate posters, but it does not adequately warn about privacy, metadata leakage, or risks of accessing untrusted external content. In an agent setting, this can lead to unintended outbound requests, exposure of internal network context, or processing sensitive links without informed consent.

VirusTotal

63/63 vendors flagged this skill as clean.