ClawHub
Back to skill

Security audit

Sendlane

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Sendlane connector wrapper with read, write, and delete capabilities, and its state-changing actions include user-confirmation requirements.

Install this only if you want the agent to manage Sendlane through OOMOL. Review write and delete confirmations carefully, especially delete_list and delete_tag, and only complete the OOMOL CLI install/login/connection steps if you trust OOMOL with this integration.

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 description instructs the agent to use this skill for ANY Sendlane request, including read, write, and delete operations, which creates an overly broad trigger surface. In an automated routing context, this can cause the skill to be selected for loosely related prompts and increase the chance of unintended state-changing or destructive actions being initiated without sufficiently narrow intent matching.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.