ClawHub
Back to skill

Security audit

Epic Leek Daily

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language A-share research-note workflow that fetches market data, reads a named knowledge base, and saves or syncs the generated note to stated destinations.

Install this only if you want an automated Chinese A-share research-note workflow that can read from your named IMA knowledge base and save or sync generated investment notes. Review the fixed local path and IMA destination first, especially if your notes may contain portfolio views, watchlists, or trading plans.

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 trigger phrases are broad and include generic requests such as '做个今日笔记' and '生成投研笔记', which can cause the skill to activate in situations where the user did not explicitly intend to run a data-fetching and persistence workflow. Because this skill also writes local files and syncs content to an external knowledge base, accidental invocation expands the risk from mere misrouting to unintended data collection, storage, and transmission.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly instructs writing a markdown file to a fixed local path and duplicating the content into an external IMA knowledge base, but it does not require clear user notice or consent about persistence and outbound transmission. In a note-generation context, the content may include portfolio views, watchlists, trading plans, or other sensitive financial information, making silent storage and synchronization a meaningful confidentiality and privacy risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest description is entirely written to operate in Chinese and the trigger phrases are Chinese-only, implying a fixed language/locale expectation. The file does not offer users a language choice or explain that the skill is intentionally limited to a Chinese-speaking or region-specific audience.

Content

No source excerpt is available for this finding.