ClawHub
Back to skill

Security audit

Teamcamp

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a Teamcamp integration with no malware signal, though its trigger wording is broad enough that users should be deliberate about when it is invoked.

Install only if you intend to let the agent work with Teamcamp. Be explicit about read-only versus state-changing requests, and review any proposed create, update, or delete action before approving it.

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
91% confidence
Finding
The trigger text is overly broad: 'Use this skill for ANY Teamcamp request' and 'Whenever a task involves Teamcamp, use this skill instead of calling the API directly' can cause the agent to invoke the skill for any mention of Teamcamp, including incidental references or tasks better handled by another tool. Overbroad routing increases the chance of unintended data access or state-changing operations being initiated in the wrong context, especially because the skill includes both read and write capabilities.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.