ClawHub
Back to skill

Security audit

IMAP/SMTP Email - Maddy Fix

Security checks across malware telemetry and agentic risk

Overview

This email skill does what it claims, but it gives the agent real mailbox access and stores email credentials locally, so users should install it only for accounts they are comfortable exposing to the tool.

Use a dedicated app password or provider authorization code rather than your main account password. Keep ALLOWED_READ_DIRS and ALLOWED_WRITE_DIRS narrow, review recipients and attachments before sending, and treat downloaded email attachments as untrusted files.

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 (3)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The security notes do not clearly warn that the skill can change mailbox state and write downloaded email attachments to local disk. This omission increases the risk of unintended data modification or local exposure of sensitive attachments, especially in agentic contexts where a user may assume the tool is passive or read-only.

Missing User Warnings

Medium
Confidence
78% confidence
Finding
The test command sends an actual outbound email to the configured account after verify(), which can create side effects that are not obvious from a safety perspective. In an agent-skill context, a caller may expect a non-invasive connectivity check, but this implementation performs a real send that could leak operational metadata, generate unwanted mail, or be abused to trigger mailbox workflows.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script collects an email address and password/app password, then writes them in plaintext to a local .env file. Although it later applies restrictive file permissions, storing long-lived mailbox credentials on disk materially increases exposure to local compromise, backups, accidental disclosure, or other tooling that reads dotfiles; the script also does not clearly warn the user before persistence.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
scripts/imap.js:78