Chatwork

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Chatwork connector that can read and change Chatwork data through OOMOL, with confirmation instructions for writes and deletes.

Install this only if you trust OOMOL's connector path with your Chatwork account. Review requested actions before approval, especially posting, updating, creating tasks, or deleting messages, because those change shared Chatwork data.

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 instruction to use this skill for "ANY Chatwork request" is overly broad and can cause the agent to invoke the skill whenever Chatwork is merely mentioned, rather than when the user actually intends an external action. In an agent setting, ambiguous routing increases the chance of unintended data access or state-changing operations being selected without sufficient narrowing of user intent.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal