Back to skill

Security audit

Agent Onboarding

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language onboarding skill for group-chat agents that creates local notes and updates agent guidance, with no code execution, network use, credential handling, or hidden behavior found.

Install this if you want Chinese-language group-chat onboarding conventions and local memory/project-note templates. Be aware it may lead an agent to update AGENTS.md and persistent memory files, so invoke it intentionally and review those changes if your workspace has different onboarding or language preferences.

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
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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger description uses broad phrases such as '教新成员', '更新 AGENTS.md', and '快速上手群聊', which can match many ordinary collaboration requests and cause the skill to activate outside its intended scope. Over-broad activation can lead to unintended modification of onboarding, memory, or AGENTS.md files and can override more appropriate skills or workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file's natural-language content is entirely in Chinese and presents the workflow as the required operating mode, with no indication that the user can choose another language or locale. Under the policy, mandating a specific language without opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This file’s instructional content is entirely in Chinese and does not mention that users may choose another language or locale. Under the policy for natural-language violations, forcing a specific language without opt-in can be a policy issue when no justification is provided.

Content

No source excerpt is available for this finding.