测试审核记录保存4

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a broad workflow-guidance skill with usability and scoping caveats, but no evidence of hidden, destructive, credential-stealing, or exfiltrating behavior was provided.

Install only if you are comfortable with a skill that may activate broadly during creative or planning work. Review its language behavior and make sure important confirmations are in a language you fully understand before allowing document changes or other consequential outputs.

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: 91% confidence
Finding: 该技能的触发描述为“在任何创造性工作之前必须使用”，范围过宽且带有强制性，容易在大量普通开发或创作场景中被意外调用。这会放大该技能对工作流的影响，使其在不必要时介入项目上下文查看、提问和文档写入流程，增加误触发、上下文过度收集和流程劫持风险。

Natural-Language Policy Violations

Medium

Confidence: 84% confidence
Finding: 技能元数据和内容均默认以中文进行交互，但没有说明这是基于用户偏好、部署环境还是业务要求，也未提供语言协商机制。这可能导致与用户语言不一致时产生误解、错误确认设计内容，甚至让用户难以及时发现文档写入、git 提交等高影响操作的真实含义。

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal