ClawHub
Back to skill

Security audit

Todoist

Security checks across malware telemetry and agentic risk

Overview

This appears to be a normal Todoist integration skill, with the main caveat that its trigger wording is broader than ideal.

Install this only if you want your agent to use your Todoist account. Review any task creation, update, completion, or deletion requests before allowing them, especially if the user request is ambiguous or only mentions Todoist in passing.

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
84% confidence
Finding
The description says to use this skill for ANY Todoist request and instead of calling the API directly, which makes routing extremely broad. In agentic systems, overly broad trigger language can cause the skill to activate in loosely related contexts, increasing the chance of unnecessary tool use, unintended data access, or bypass of more specific safety logic.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.