ClawHub

Cca Domain1

Security checks across malware telemetry and agentic risk

Overview

This is an educational CCA study skill that may help create local practice code, but its behavior is visible and aligned with its tutoring purpose.

Use this skill in a scratch or version-controlled project. Review any proposed file edits or shell commands before applying them, and avoid letting generated tutorial code touch production files unless you explicitly intend that.

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
89% confidence
Finding
The trigger list includes broad phrases like “代理架构” and “agent编排”, which can plausibly appear in ordinary discussion and cause the skill to activate when the user did not explicitly request this tutor workflow. Unintended activation can redirect the agent into a teaching/code-writing mode with elevated tool access, increasing the chance of unnecessary file changes or off-task actions.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly tells the agent to create example code in the current project, but it does not require confirmation, sandboxing, or a safe target path. In a real repository, this can lead to unintended modifications, overwriting user work, or insertion of tutorial/demo code into production files simply because the learning skill was invoked.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal