ClawHub
Back to skill

Security audit

Sender

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Sender connector that can read and change Sender data through OOMOL, with write and destructive actions labeled and confirmation required.

Install only if you intend to let your agent operate your Sender account through OOMOL. Treat subscriber creation, updates, and group removals as real account changes, and require the agent to show the exact payload before approving any write or destructive action.

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
90% confidence
Finding
The description says to use this skill for ANY Sender request instead of calling the API directly, which is broad enough to trigger the skill for a wide range of Sender-related tasks without clear scoping. In a skill that includes write and destructive operations, this increases the chance of unintended activation and can lead to accidental data modification or deletion if an agent routes a task here too aggressively.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.