ClawHub
Back to skill

Security audit

SZZG007 Email Business Manager

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent email-management helper, but it would handle sensitive mailbox, customer-history, and credential data with broad triggers and limited user-control detail.

Review before installing. Use a dedicated mailbox or least-privilege account, avoid reusing high-value email credentials, and require explicit confirmation before the skill reads, searches, classifies, syncs, or drafts from mailbox history. Treat the encryption, access-control, and logging claims as unverified unless supplied by a separate implementation.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description presents convenient email-management features but does not explicitly warn users that the skill may access mailbox contents, customer communication history, local storage paths, and configured credentials. Because this skill operates on highly sensitive business communications and customer data, the missing disclosure increases the risk of uninformed use and accidental overexposure of private or regulated information.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are generic natural-language requests such as viewing customer communication history, replying to emails, and classifying mail, which overlap with common assistant interactions. In a system with multiple skills, this can cause the skill to activate unexpectedly and gain access to sensitive email content, customer histories, and business context without the user clearly intending to invoke this specific capability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.