ClawHub
Back to skill

Security audit

学习计划与复盘台

Security checks for vulnerabilities and agentic risk

Overview

This is a simple study-planning prompt skill with no code execution, credential access, network behavior, or persistence.

Safe to install for study-plan generation. Users should be aware it may activate on broad frustration or formatting requests, so it would be better if future versions narrow those triggers to explicit study or exam-planning language.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrase "坚持不下去" is broad distress-related language that can appear in many unrelated or emotionally sensitive conversations. This can cause unintended activation of the skill when a user is expressing general frustration rather than explicitly requesting study-planning help, increasing the chance of context hijacking or inappropriate responses in sensitive situations.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The natural-language examples are generic enough that they may match broad user requests without clearly anchoring activation to this specific skill. Overly general invocation patterns can lead to accidental routing, unexpected skill activation, and reduced reliability when users are asking for adjacent but different help.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.