ClawHub
Back to skill

Security audit

ymailink

Security checks across malware telemetry and agentic risk

Overview

The skill is a legitimate terminal email helper, but it should be reviewed carefully because it can access and change mailboxes, handle credentials, and send selected email content to an external AI service.

Install only if you are comfortable giving ymailink access to the relevant email accounts. Prefer OAuth, system keyring, or password-manager commands over raw passwords in config, restrict config file permissions, verify the upstream package source, and avoid AI commands on confidential mail unless you explicitly accept sending that message content to the external AI service.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

High
Confidence
95% confidence
Finding
The trigger language explicitly says to use this skill anytime the user mentions email in the terminal, including authentication, automation, troubleshooting, message handling, and AI summarization. That scope is so broad it can cause the agent to invoke a high-privilege email-management tool in many situations where a narrower or safer skill-selection policy would be more appropriate, increasing the chance of unintended access to sensitive mail, credentials, or destructive actions.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documentation states that AI summary and reply features send fetched email contents to an external AI API, but it does not present a clear privacy warning adjacent to the feature description. In an email client context, messages often contain sensitive personal, corporate, financial, or regulated data, so silent transmission to a third-party service creates a real confidentiality and compliance risk.

Session Persistence

Medium
Category
Rogue Agent
Content
ymailink account configure
```

This prompts for account details and prints the resulting TOML config to stdout. **It does not write the file** — you need to copy-paste the output to `~/.config/ymailink/config.toml`.

See `references/configuration.md` for manual config setup with all backend types (IMAP/SMTP, Outlook, Gmail, Gmail-via-IMAP, Exchange), password auth methods (raw/cmd/keyring), OAuth2 token management, folder aliases, signatures, download directories, and proxy support.
Confidence
79% confidence
Finding
write the file** — you need to copy-paste the output to `~/.config

VirusTotal

60/60 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
references/configuration.md:96