ClawHub
Back to skill

Security audit

Multi-Perspective Forum

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only debate skill, but it also recommends recurring LLM-powered audits that may send business metrics and logs without clear approval or scoping controls.

Use manually unless you intentionally want recurring audits. Before enabling cron, decide exactly which data sources are allowed, redact customer data and sensitive logs, and confirm how to disable the scheduled jobs.

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
88% confidence
Finding
The skill advertises generic trigger phrases such as 'debate this' and 'weekly retro', which can easily occur in normal conversation and unintentionally invoke the skill. In an agent environment, this can cause unauthorized or unexpected execution, potentially sending sensitive context into the forum prompt and consuming model/runtime resources without clear user intent.

Static analysis

No suspicious patterns detected.