ClawHub
Back to skill

Security audit

Discuss Before Begin

Security checks for vulnerabilities and agentic risk

Overview

This is a planning-discussion skill with broad activation wording, but it contains no hidden code, credential access, persistence, or destructive behavior.

Install this if you want the agent to slow down and challenge requirements before building. Be aware that its broad triggers may make it take over general planning requests, and it will intentionally delay implementation until you explicitly confirm consensus.

SkillSpector

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 very broad trigger phrases such as 'I want to do X', 'help me explore', and 'design a solution', which can match a wide range of ordinary user requests and cause the skill to activate unexpectedly. Unintended invocation can override a more appropriate workflow, push the conversation into an aggressive requirement-interrogation mode, and create confusion or unsafe delegation boundaries in multi-skill environments.

Static analysis

No suspicious patterns detected.