ClawHub
Back to skill

Security audit

Email Triage Pro

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for email triage, but it can access a sensitive inbox through existing web sessions from broad, casual triggers without an explicit confirmation step.

Review this skill before installing if you keep sensitive mail in your browser session. It should be used only when you deliberately want the agent to inspect a specific mailbox, and you should confirm drafts before sending because the skill itself only prepares replies.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises broad triggers like 'check my email', 'any urgent emails', and 'draft a reply', which are common conversational phrases and can cause the agent to invoke this skill in situations where the user did not intend mailbox access. Because the skill fetches live email content via browser/web access, accidental activation can expose sensitive inbox data and draft actions in an overbroad context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The quick-command list includes ambiguous triggers such as 'check email', 'check urgent', 'email summary', and 'follow up' without requiring account, source, or permission confirmation. In this skill's context, those phrases directly lead to inbox retrieval and analysis, increasing the risk of unintended access to highly sensitive communications if the orchestrator matches on casual user language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.