ClawHub
Back to skill

Security audit

email-skill

Security checks for vulnerabilities and agentic risk

Overview

This email skill is transparent about what it does, but it embeds live SMTP credentials and enables arbitrary outbound email without enough guardrails.

Review this skill carefully before installing. Only use it if you intentionally want this agent to send email through the documented yeah.net account, and rotate/remove the embedded SMTP password first if the skill will be shared, logged, or stored anywhere outside a trusted private workspace.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:28
Finding

Hardcoded Live SMTP Credentials

Content
View full analysis
Remediation
View remediation

SkillSpector

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill explicitly instructs an agent to create and run a script that transmits data to an external SMTP service using embedded live credentials, but it does not provide a meaningful safety warning, consent check, or data-handling restriction for outbound transmission. In an agent setting, this makes exfiltration and unauthorized external communication easier because arbitrary recipient, subject, and body content can be sent off-host with a one-shot command.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.