ClawHub
Back to skill

Security audit

Training Checklist

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain training-preparation checklist helper with minor routing ambiguity but no hidden code, data access, persistence, or unsafe authority.

Before installing, expect this skill to help structure training preparation tasks and progress reports. Its generic reminder/to-do triggers may activate in some unrelated planning conversations, so users who want precise routing should narrow the trigger phrases, but no sensitive access or hidden execution was found.

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
93% confidence
Finding

The trigger keywords include broad everyday phrases such as '提醒' and '待办事项', which can cause the skill to activate in unrelated conversations. This increases the chance of unintended invocation, confusing routing, and accidental processing of user content outside the intended training-preparation context.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This manifest file only provides a broad capability description of a training-preparation checklist, but does not specify what exact user requests should or should not invoke the skill. Without explicit trigger phrases, scope boundaries, or exclusion examples, the activation condition is underspecified and could lead to unintended invocation for general training-related conversations.

Content

No source excerpt is available for this finding.