小红书爆款文案助手

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Xiaohongshu copywriting helper that sends user-provided copywriting inputs to the AI Skills service, with no evidence of hidden local access or destructive behavior.

Install only if you are comfortable sending the topic, audience, selling points, account persona, and related prompt content to ai-skills.ai using your AI Skills API key. Prefer invoking it explicitly for Xiaohongshu copywriting tasks, and avoid entering secrets, customer data, or confidential campaign material unless that service's data handling is acceptable.

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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The manifest enables implicit invocation globally but provides no trigger constraints, examples, or narrowing conditions. This can cause the agent to invoke the skill in unintended contexts, increasing the chance of prompt-scope overreach, unexpected data exposure to the skill, or user confusion about why the skill was activated.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal