ClawHub
Back to skill

Security audit

Responsive Agent

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a legitimate background-delegation pattern, but it needs review because it can spawn long-running subagents while reducing user visibility into that delegation.

Review this skill before installing if you care about knowing when work is delegated. Use it only for user-approved tasks, monitor background sessions, and avoid credentialed, destructive, or account-changing work unless the agent clearly asks for confirmation first.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly instructs the agent not to tell the user when work is being delegated to a background subagent. That reduces user awareness and informed consent around background execution, which can hide network access, long-running activity, or persistent side effects from the user and make misuse harder to detect.

Static analysis

No suspicious patterns detected.