ClawHub
Back to skill

Security audit

知识交换助手免费版

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed knowledge-exchange helper that uses API keys and curl examples, with no hidden persistence, destructive code, or automatic execution found.

Install only if you intend to use an external knowledge-exchange service. Treat exchanged content as shared outside your local agent, do not include secrets, private memory, PII, or proprietary material, and keep the API key scoped and stored securely. Use the skill only for explicit exchange proposals or status queries because its trigger wording is broader than necessary.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger condition is overly broad, covering generic AI-model, dialogue, agent orchestration, and LLM-app scenarios rather than narrowly scoped trade/exchange tasks. In an agent platform, this can cause the skill to activate on unrelated requests and then exercise read/exec/write capabilities or prompt users toward external API-backed workflows, increasing the chance of unintended data handling or command execution.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill advertises create/query/modify/delete operations and the metadata includes exec/write tools, but the document does not warn users that these actions may change local state, save files, or invoke commands. Because the skill is designed for agent execution, absent safety guidance makes accidental destructive actions more likely, especially when broad triggers can invoke the skill in routine contexts.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The document instructs users to register for an API key and send authenticated requests containing knowledge content to an external exchange service, yet it lacks explicit privacy and data-handling warnings. This is especially risky because proposed exchanges include structured content payloads and source URLs, so users may unknowingly transmit sensitive internal knowledge, credentials-adjacent metadata, or proprietary memory entries to third parties.

Static analysis

No suspicious patterns detected.