ClawHub
Back to skill

Security audit

Northflank

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Northflank helper that uses OOMOL's oo CLI for read-only project and service lookups, with no artifact evidence of hidden collection or destructive behavior.

Install only if you are comfortable connecting Northflank to OOMOL and letting the agent read project and service metadata through that connector. Treat the documented CLI install command as a normal third-party installer step and review it before running if the oo CLI is not already installed.

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 says to use this skill for ANY Northflank request and instead of calling the API directly, which is broader than necessary and can cause the agent to invoke the skill in contexts the user did not explicitly request. Overly broad routing increases the chance of unintended tool use, unnecessary exposure of account-scoped data, and bypass of more precise or safer handling paths.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.