title

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu title-writing helper with no evidence of hidden access, persistence, data theft, or destructive behavior.

Install this if you want highly click-optimized Xiaohongshu/RedNote title suggestions. Review outputs before posting for accuracy, advertising-law claims, platform policy, and brand tone, especially because the skill intentionally uses emotional hooks and urgency.

SkillSpector

By NVIDIA

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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: 89% confidence
Finding: The trigger condition is broad enough to match generic user inputs such as any raw text or topic, which increases the chance this skill activates outside its intended use. In an agent environment, over-broad activation can cause unintended routing, style hijacking of unrelated requests, or prompt-context interference even without obviously malicious content.

Natural-Language Policy Violations

Medium

Confidence: 81% confidence
Finding: The skill hard-codes a specific locale/style output standard without indicating user choice or opt-in, which can override user preferences and cause unwanted language or cultural framing. This is primarily a safety and UX control issue rather than a direct exploit, but it can contribute to misrouting or inappropriate responses when the skill is invoked automatically.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal