ClawHub
Back to skill

Security audit

send-email

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward SMTP email skill, but users should be careful because it can send message content and chosen attachments outside the local environment.

Install only if you want an agent to send email through your configured SMTP account. Verify recipients, subject/body, and especially attachment paths before sending; avoid invoking the included shell helper unless you intentionally want msmtp/mutt behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill documentation instructs the agent to rely on SMTP credentials injected through environment variables, but the skill manifest does not declare any corresponding permission for env access. This creates a permission-model gap: the skill can consume sensitive runtime secrets without transparent declaration, making review and enforcement weaker and increasing the chance of unintended credential exposure or overprivileged execution.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The README explicitly instructs the agent to send emails and attachments to external recipients but provides no warning, consent requirement, or data-handling safeguards. In an agent setting, this can normalize exfiltration of user data or local files through a built-in workflow, increasing the risk of accidental or prompt-induced disclosure.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill will read any local file path supplied as an attachment and transmit its contents over email without any validation, restriction, or explicit disclosure warning. In an agent-skill context, this can enable unintended exfiltration of sensitive local files such as credentials, SSH keys, or user documents if a user or upstream agent passes an unsafe path.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.