ClawHub
Back to skill

Security audit

Knock

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Knock connector skill with write and delete capability, but its instructions keep those actions user-confirmed and scoped to Knock.

Install this only if you intend to let your agent operate Knock through OOMOL. Reads can run directly, but review every payload before approving workflow triggers, user identification updates, or permanent user deletion.

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
95% confidence
Finding
The trigger text instructs the agent to use this skill for "ANY Knock request," which is overly broad and can cause the skill to be invoked for all Knock-related tasks without sufficient scoping or policy checks. Because the skill includes write and destructive actions, broad auto-selection increases the chance of unintended data modification or deletion if the agent routes ambiguous requests here by default.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.