ClawHub
Back to skill

Security audit

office-automation-pro

Security checks for vulnerabilities and agentic risk

Overview

This office automation skill is broadly coherent, but it asks agents to handle sensitive business data and perform external actions like bulk email and content publishing without clear scoping or confirmation controls.

Review this skill carefully before installing in a work environment. Use it only with explicit file paths, recipient lists, and approval steps, and require previews or draft mode before sending emails, publishing content, touching finance or HR records, or using SMTP credentials.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill prominently advertises bulk email sending and automatic report distribution, but the warning about external transmission is not equally prominent near those capabilities. Because this skill handles HR, finance, sales, and other sensitive office data, users may trigger outbound transmission of confidential documents or reports without realizing the privacy and compliance implications.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation examples are framed as broad natural-language office requests such as sending emails, generating reports, and arranging meetings, without clear activation boundaries, confirmation gates, or scoping constraints. In an agent environment, this increases the chance of accidental or over-broad execution on sensitive files, calendars, or recipients, especially because the skill supports external actions like mail distribution and workflow automation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language interface and documentation are entirely in Chinese, and the examples imply the skill expects Chinese user commands. Under the language/locale policy, forcing a single language without user opt-in or documented justification can be a policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.