ClawHub
Back to skill

Security audit

Productivity Bot

Security checks for vulnerabilities and agentic risk

Overview

The skill is a broad productivity automation helper that discloses file processing and external notifications, but it does not clearly scope or gate those higher-impact actions.

Review this skill before installing if you plan to use it with private files, business data, API keys, webhooks, or chat/email integrations. Only enable scheduled jobs or outbound notifications when the destination and data being sent are explicit, and require confirmation before overwriting files or transmitting reports.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is broad and open-ended for an automation bot, which can cause over-activation or user misunderstanding about what actions the skill may take. In a productivity/automation context, ambiguous scope is more dangerous because the skill also references scheduled tasks, data processing, and outbound notifications, increasing the chance of unintended file operations or external actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises file processing, report generation, email/Slack/Discord messaging, and custom webhooks without warning users that it may modify files or send data externally. In an automation skill, this omission is risky because users may trigger actions that overwrite local data or exfiltrate sensitive information to third-party services without informed consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The feature list is primarily in English but includes the Chinese item "定时报告" without any explanation, opt-in, or documented locale behavior. This creates a natural-language policy concern because the skill's user-facing language appears inconsistent and may impose a language choice unexpectedly.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.