Daily-to-Goal MCP

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a goal/task management integration with disclosed external API read/write behavior, with a usability risk from broad trigger wording but no artifact-backed malicious behavior.

Before installing, confirm that you want this skill to read and write data in the Daily-to-Goal account tied to its API key. Use a least-privilege or dedicated API key if available, and be careful with generic requests like creating tasks or managing goals if you use multiple goal-tracking tools.

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 skill advertises trigger phrases such as "manage my goals", "create a task", and especially generic product references like "goal tracking", which are broad enough to match common user requests outside this specific integration. That can cause unintended invocation of a capability that performs real read/write actions against an external SaaS using a privileged API key, increasing the chance of accidental data access or modification.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal