ClawHub
Back to skill

Security audit

Weekly Checker

Security checks for vulnerabilities and agentic risk

Overview

This weekly checker is mostly purpose-aligned, but it authorizes broad sensitive security scans, scheduled notifications, and limited automatic repairs without enough scoping or redaction detail.

Review this before installing if the environment contains secrets or private project data. Require explicit path allowlists, redacted reports, approval before Feishu notifications, and a clear rule that repairs such as log deletion or gateway restart only happen after user confirmation unless separately configured.

A.I.G

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:53
Finding

Unbounded Inspection of Sensitive Host Resources and Credentials

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

L136-L142 明确写明发现问题后应“等待指示（不擅自修改）”，表示该技能的处置意图应以检查和通知为主，不主动变更系统。但 L143-L155 随后又列出可自动修复的操作示例，包括删除旧日志和重启网关服务，这与前述“不擅自修改”的说明直接冲突。

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 162)May include surrounding context.

md
## 相关文件

- 检查工具：`tools/weekly_checker.py`
- 技能文档：`skills/weekly-checker/SKILL.md`
- 检查报告：`reports/weekly_check_*.json`
- 通知模板：`reports/feishu_notification_*.txt`

Static analysis

No suspicious patterns detected.