ClawHub
Back to skill

Security audit

Task Executor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent task-execution helper, but its very broad triggers and automatic background task delegation could make it act on ordinary requests without enough user control.

Review this skill before installing if you do not want broad Chinese phrases to trigger automatic multi-step work. Use it only where background subagent execution is acceptable, and avoid storing or syncing sensitive task details unless you have separately configured retention and third-party sharing expectations.

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

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger keywords are extremely broad terms such as '帮我', '分析', '调研', and '写报告', which overlap with ordinary user conversation and can cause the skill to activate unintentionally. In a skill that can automatically decompose work, spawn subagents, and perform parallel execution, accidental invocation can lead to unintended actions, excess resource consumption, and processing of sensitive user requests without clear consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The natural-language instructions, examples, and user-facing trigger phrases are entirely in Chinese, which can impose a language-specific interaction pattern without any stated user opt-in or justification. Under the policy, forcing a specific language is a potential locale-policy violation unless the skill offers a choice or clearly documents why the locale is required.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill documents local task-state storage in 'memory/tasks/active.json' and optional synchronization to a third-party Feishu spreadsheet, but it does not warn users that their requests, statuses, and results may be persisted or externally synced. Because this skill is intended for research, analysis, and report-writing workflows, stored task content may include sensitive business, personal, or confidential information, creating privacy and data-governance risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.