ClawHub
Back to skill

Security audit

demo-lin-test

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple document-summarization prompt with minor clarity issues but no privileged actions, persistence, code execution, or data exfiltration behavior.

Before installing, users should know this skill is intended for summarizing provided technical text into Markdown. Its trigger and output language rules could be clearer, so users may want to invoke it explicitly and review whether the mixed Chinese-English headings match their workflow.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The activation condition '当用户要求 林大大文档时，使用此技能' is ambiguous and underspecified, which can cause the skill to trigger in unintended contexts. Overbroad activation increases the chance of misrouting user requests, causing the agent to apply summarization behavior when it is not appropriate and potentially mishandling user intent or sensitive content.

Natural-Language Policy Violations

Low
Confidence
82% confidence
Finding
The file contains output instructions in both Chinese and English, including section headings like 'Key Points', 'Risks', and 'Output Format', without stating whether the output language should follow user preference. This can impose a language choice implicitly rather than offering opt-in or matching the user's locale.

Static analysis

No suspicious patterns detected.