ClawHub
Back to skill

Security audit

Mp Diagnose

Security checks for vulnerabilities and agentic risk

Overview

This skill is a debugging workflow guide with no executable code, hidden behavior, credential handling, persistence, or network exfiltration instructions.

Install this if you want a structured debugging discipline. Expect it to encourage tests, local scripts, profiling, temporary logs, and cleanup; review any proposed code or environment changes as you normally would for bug-fix work.

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
95% confidence
Finding

The manifest description is overly broad and does not clearly constrain when the skill should be invoked. Ambiguous trigger text can cause the agent to select this skill in unintended contexts, increasing the risk of misuse, confused-deputy behavior, or accidental execution outside its intended diagnostic scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

Line L003 embeds the invocation guidance in Chinese only for part of the trigger description ("当用户需要排错、debug、诊断问题、bug修复、性能回归分析时使用") without stating that the skill is intended for a Chinese-speaking context or offering alternative language/locale handling. This is a natural-language locale policy concern because it imposes a specific language expectation without opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.