ClawHub
Back to skill

Security audit

Shitty Email

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward temporary email inbox helper, with expected external email API use and no hidden code or persistence.

Install only if you are comfortable using the shitty.email service for temporary inbound mail. Treat inbox tokens like short-lived credentials, avoid sharing them, and use disposable addresses only where you are authorized and where doing so does not violate site rules or bypass anti-abuse checks.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tool Parameter Abuse

High
Category
Tool Misuse
Content
→ Fetch email content, extract the code pattern, return it

User: "I'm done, delete the inbox"
→ Call DELETE /api/inbox with the token
Confidence
80% confidence
Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly promotes using disposable email addresses to sign up for third-party services, which can facilitate policy evasion, throwaway account creation, and reduced accountability. In this context, the capability is not inherently malicious, but the lack of guardrails or warnings makes misuse substantially easier.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill tells the agent to store and reuse the inbox token but does not identify the token as a secret or explain that possession grants full access to mailbox contents and lifecycle actions. This can lead to accidental exposure in logs, chat transcripts, memory, or downstream tools, enabling unauthorized reading or deletion of emails.

Static analysis

No suspicious patterns detected.