ClawHub
Back to skill

Security audit

踩坑记录

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed lessons-learned note system that stores searchable Markdown records, with reasonable limits around sensitive data and user-controlled file locations.

Install this only if you want the assistant to maintain a persistent lessons-learned log. Choose a specific storage folder, review entries before they are saved if they may include private context, and avoid using it for secrets, account details, IDs, or personnel judgments.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises activation on very broad, everyday phrases like '记一下这个坑' or '整理踩坑记录' without tighter gating conditions. This can cause the agent to trigger in contexts where the user did not intend persistent logging or file operations, leading to unintended storage of conversation content or unnecessary writes to local/project files.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.