ClawHub
Back to skill

Security audit

Workflow Dlc Agent Phasing

Security checks across malware telemetry and agentic risk

Overview

This is a planning-only skill for phasing Agent product roadmaps, with no executable code, credential use, network access, or hidden high-impact behavior.

Install this if you want a Chinese-language workflow for Agent product phase planning. Be aware that generic phrases like 'Agent 规划' may activate it in broad planning conversations, so users should confirm the context is product roadmap phasing when the skill is invoked.

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

Medium
Confidence
90% confidence
Finding
The skill declares broad trigger phrases such as "Agent 规划", "P0 P1 分期", and "Agent 路线图" without any routing constraints, exclusions, or disambiguation rules. This can cause the skill to activate in unrelated planning conversations, leading to prompt hijacking of user intent, workflow misrouting, and unintended access to linked assets or downstream actions.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.