ClawHub
Back to skill

Security audit

Planhat

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Planhat connector that can read and update Planhat records through OOMOL, with write actions called out for user confirmation.

Install only if you want Codex to use your OOMOL-connected Planhat account. Review write payloads carefully before approving create or update actions, because they can change business/customer records in Planhat.

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 phrase 'Use this skill for ANY Planhat request' creates an overly broad activation scope that can cause the agent to invoke this skill for loosely related tasks without sufficient narrowing. In a connector skill that supports both read and write operations, unnecessary invocation increases the chance of unintended data access or state-changing actions, especially if downstream prompting or user intent is ambiguous.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.