Back to skill

Security audit

Doctor Check

Security checks for vulnerabilities and agentic risk

Overview

This is a simple diagnostic instruction skill with disclosed local checks and no bundled executable code, persistence, or exfiltration behavior.

Install only if you want a Chinese-language doctor-style diagnostic helper. Be aware that diagnostics may inspect local configuration, service status, permissions, API-key validity, and logs, so review outputs before sharing them and prefer invoking it explicitly by name.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation phrases "系统诊断" and especially "检查问题" are generic and likely to appear in normal user conversations, which can cause the skill to activate unintentionally. Because this skill performs environment, service, configuration, and log checks, accidental triggering could expose sensitive operational details or cause the agent to take diagnostic actions outside the user's intended scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The entire skill metadata and user-facing documentation are written only in Chinese, with no indication that users may choose another language or locale. This can violate language/locale policy when a skill implicitly enforces one language for all users without documented opt-in or justification.

Content

No source excerpt is available for this finding.