ClawHub
Back to skill

Security audit

Laposta

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Laposta connector that can read and update mailing-list data through OOMOL, with user confirmation required before writes.

Install this only if you intend to let the agent operate your Laposta mailing-list data through OOMOL. Review write payloads carefully before approval, and only run the CLI install or auth setup when you trust the OOMOL tooling and need the connector.

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
89% confidence
Finding
The skill metadata and description instruct the agent to use this skill for ANY Laposta-related request, which is an overly broad trigger that can cause the skill to preempt safer or more specific handling paths. In practice, this increases the chance the agent will route unrelated, ambiguous, or higher-risk Laposta tasks through shell-mediated connector commands without sufficient task-level scrutiny.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.