ClawHub
Back to skill

Security audit

Explain Code 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This skill only changes how code explanations are written and does not request execution, persistence, credentials, network access, or file mutation.

Install this if you want code explanations to use analogies, ASCII diagrams, and step-by-step walkthroughs. Be aware it may activate for broad 'how does this work' questions and may bias responses toward Chinese unless the user or system asks for another language.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
96% confidence
Finding

The skill description is broad enough to trigger on generic requests about 'how something works' or teaching a codebase, which can cause the agent to invoke this skill in situations beyond narrow code-explanation use cases. Over-broad activation increases the chance of unintended routing, instruction interference, or disclosure of contextual code details when a more appropriate skill or default behavior should handle the request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill metadata and body are written entirely in Chinese and instruct a fixed explanation style without giving the user a language choice, which can force outputs into a language the user did not request. This can degrade safety and usability by causing misunderstandings, misinterpretation of code guidance, or failure to communicate important caveats clearly in multilingual environments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.