个人品牌故事

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only writing aid for personal brand stories, with no executable behavior or hidden system access, though users should avoid oversharing private details.

Install only if you want a personal-brand storytelling assistant. When using it, avoid exact salaries, private health or family details, addresses, or third-party names unless they are necessary and you have consent; use approximate or anonymized details for public drafts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The reference explicitly instructs the agent to imitate a named person's tone, structure, and technique patterns, which can override user-preferred voice or style if this material is used as an active prompt source. While not directly a code-execution or data-exfiltration issue, it is a real prompt-quality and alignment vulnerability because it can cause unauthorized persona steering and produce misleading or inauthentic outputs without user opt-in.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal