Security audit

casual-history-article

Security checks across malware telemetry and agentic risk

Overview

This is a purpose-aligned Chinese writing style skill for casual history articles, with no executable code or hidden data access.

Install this if you want an agent to produce Chinese casual-history articles with a specific narrative style. Be aware that it may strongly shape tone, structure, and language when activated, so explicitly state a different language or format if needed.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (2)

Vague Triggers

Medium

Confidence: 85% confidence
Finding: The activation description is broad enough to match many ordinary writing requests, which can cause the skill to be invoked when the user did not specifically ask for this style or domain behavior. That increases the risk of unintended instruction override at the routing layer, especially because the skill also imposes a specific tone, structure, and domain framing that may not fit the user's actual request.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The skill description mandates Chinese output without stating that this depends on user preference, which can override the user's requested language or system-level language behavior. In a multi-skill environment, this creates a prompt-scope problem where activation of the skill may silently force output language, reducing user control and potentially causing incorrect or unusable responses.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.