Skill Creator Attach Info

Security checks across malware telemetry and agentic risk

Overview

This is a narrow helper that adds metadata to newly created skill files, with no executable code, network behavior, credentials, or hidden actions found.

Install only if you want newly created skills to receive these metadata fields automatically. Before accepting edits, confirm the target SKILL.md path, the BusinessSupportVersion value, and whether publishing your local username as Author 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 (2)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger conditions include very common phrases such as '创建技能', '新建技能', and '添加技能', which can match ordinary user requests without sufficient scoping to a specific trusted workflow. This can cause unintended automatic invocation and file modification behavior, increasing the risk of surprise actions or policy bypass in multi-skill environments.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The skill mandates automatic invocation on loosely defined indirect conditions, including after any `skill-creator` use or after writing a `.trae/skills/xxx/SKILL.md` file. Because these conditions are broad and underspecified, the agent may invoke the skill in unintended contexts and perform unauthorized edits or command execution steps.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal