ClawHub
Back to skill

Security audit

个人发展复盘助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local personal-review formatter that asks to analyze user-provided text or files, with no evidence of hidden execution, network access, persistence, or data exfiltration.

Install only if you are comfortable giving the skill the specific journal, note, or record files you want reviewed. Avoid using it on credential files, browser profiles, SSH keys, system configuration, or unrelated private documents.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly invites users to provide a local file path and states it can access that path via the read_file tool, but it does not warn about the risk of exposing sensitive local files. This creates a real data-exposure risk because users may paste or be induced to provide paths to secrets, personal documents, or system files, and the skill is designed to process whatever is read.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The instruction explicitly requires '中文输出', forcing a specific language regardless of user preference. This is a natural-language policy concern because it imposes a locale/language constraint without offering opt-in or an alternative.

Static analysis

No suspicious patterns detected.