ClawHub
Back to skill

Security audit

yanyan-10agents

Security checks across malware telemetry and agentic risk

Overview

This is a single-file product-management assistant skill with broad trigger wording but no code, credentials, network access, persistence, or destructive behavior.

Safe to install for product strategy, PRD drafting, roadmap, and GTM planning. Be aware it may activate on broad product-related wording and uses a Chinese-language persona/opening, so disable or edit it if you want narrower routing or language mirroring.

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

High
Confidence
96% confidence
Finding
The skill description mandates invocation for very broad, common product-related terms such as '产品', '功能', '迭代', and 'PRD', which can cause the agent to over-trigger this skill in many unrelated or only tangentially related conversations. This creates routing/control-risk: the skill may hijack normal agent behavior, reduce user intent fidelity, and expand the influence of the skill beyond an appropriately scoped domain.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.