ClawHub
Back to skill

Security audit

Postmark

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Postmark connector skill that discloses its email-sending and template-management powers and requires confirmation before write actions.

Install only if you trust OOMOL and intend to let the agent use your connected Postmark account. Review payloads carefully before approving email sends, batch sends, or template edits, and inspect the oo CLI install script if it needs to be installed for the first time.

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
93% confidence
Finding
The skill description says to use this skill for ANY Postmark request and instead of calling the API directly, which creates an overly broad routing trigger. That can cause the agent to invoke this skill for sensitive or high-impact Postmark operations without sufficient task-specific narrowing, increasing the chance of unintended email sends, template edits, or data access.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.