ClawHub

Outlook Email

Security checks across malware telemetry and agentic risk

Overview

This Outlook email skill matches its stated purpose, but it can read and send real email through a linked mailbox without documenting confirmation or draft safeguards.

Review before installing. Only use this with a mailbox you are comfortable linking through MorphixAI, verify the external plugin source, and require manual review of account, recipients, subject, and full message body before any send or reply action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill enables outbound actions such as sending and replying to emails to external recipients, but it does not warn that these operations can have real-world consequences like data leakage, accidental disclosure, or unintended communication. In an agent context, this is especially risky because users may treat examples as safe defaults and trigger external actions without explicit confirmation or awareness.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The setup instructions tell users to place an API key in an environment variable but provide no guidance on secure credential handling, such as avoiding hardcoding, shell history exposure, logs, screenshots, or source control leaks. While using environment variables is common practice, omitting basic secret-handling warnings can still contribute to accidental credential exposure.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal