Back to skill

Security audit

Diagnose

Security checks for vulnerabilities and agentic risk

Overview

This is a structured debugging guidance skill with some broad triggers and sensitive-tool advice, but no hidden execution, persistence, exfiltration, or destructive behavior was found.

Install this only if you want a Chinese-language structured debugging workflow. Before following its tool suggestions, confirm any shell command yourself and avoid using packet capture, proxying, or system tracing on production or sensitive data unless you are authorized and can redact secrets.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
name: diagnose
version: 3.0.0
description: "Debug issues through structured 5-stage methodology �� build feedback loop, reproduce, hypothesiz..."

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description says the skill loads automatically when a task is classified as "排错/debug", but it does not define the exact trigger scope, boundaries, or exclusion conditions. Because "debug" is a common term used in many routine coding conversations, this could cause unintended invocation without clearer constraints or negative examples.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly contemplates using exec to run debugging commands, but it does not require explicit user confirmation or a clear user-facing warning at the point of execution. In a debugging context, commands may be derived from logs, hypotheses, or repository context, so allowing shell execution without a strict approval boundary increases the risk of unsafe command execution, especially when handling adversarial error output or untrusted projects.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The description is written entirely in Chinese and presents the skill behavior in a single locale without indicating that other languages are supported or that the user can choose their preferred language. This can constitute a language/locale policy violation when no opt-in or justification is provided.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list is broad and includes generic terms like "debug", "诊断", and "错误分析", which can match many normal coding requests and cause this skill to activate unexpectedly. In an agent system, unintended activation can override a more appropriate skill's behavior, increasing the chance of mis-scoped actions or confusing output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The entire skill reference is written in Chinese, but there is no indication that the user opted into Chinese or that the document is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown section recommends HTTP capture and interception tools such as curl -v, Chrome DevTools Network, and mitmproxy, which can expose authentication headers, cookies, request bodies, and other sensitive user data during debugging. The file provides no user-facing warning about handling captured traffic safely or avoiding use on sensitive production data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The Linux and Windows system-level tooling section includes strace, tcpdump, Wireshark, and Process Monitor, all of which can capture detailed process activity, file access, and network contents. Because these behaviors can affect privacy and reveal sensitive system information, the skill description should warn users before suggesting such tools.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The file title and all instructional content are written entirely in Chinese, with no indication that alternative languages are available or that the locale restriction is intentional. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.