副业验证 skill

Security checks across malware telemetry and agentic risk

Overview

This is a coherent side-project validation skill whose main risk is that optional research scripts send idea keywords to public web services.

Install if you want a Chinese-language workflow for validating side-project ideas. Avoid giving the scripts confidential product names, proprietary concepts, or sensitive keywords because they may be sent to third-party search and API services; review the small shell scripts first if your environment restricts command or network use.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 93% confidence
Finding: The skill instructs the agent to use local shell scripts (`scripts/research-demand.sh`, `scripts/find-competitors.sh`, `scripts/search-trend.sh`) but does not declare the corresponding permissions. Undeclared code-execution capability creates a trust and review gap: the runtime may execute scripts users and reviewers did not explicitly authorize, and those scripts could perform unintended local actions or network access depending on implementation.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The trigger section includes catch-all wording such as '类似的产品/副业验证需求', which is broad enough to activate on many generic requests about ideas, products, or markets. Overbroad activation can cause the skill to run outside its intended scope, increasing the chance it invokes research scripts or produces authoritative business guidance when the user did not ask for this specific workflow.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal