ClawHub
Back to skill

Security audit

Check Emails 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This skill simply runs a disclosed Himalaya command to list recent email envelopes, with the main caution being a broad trigger phrase for sensitive mailbox access.

Install only if you already use Himalaya and are comfortable with the agent listing recent mailbox envelopes when you ask it to check email. Prefer explicit wording such as `check my email with Himalaya` if you want to avoid accidental invocation.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrase "check emails or similar" is overly broad and can cause the skill to run on loosely related user input without clear confirmation. Because the command accesses a user's mailbox, unintended invocation could expose sensitive email metadata or contents in contexts where the user did not explicitly request mail access.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.