Back to skill

Security audit

explain-code

Security checks for vulnerabilities and agentic risk

Overview

This is a simple code-explanation skill that changes answer style but does not request sensitive access, run code, install anything, or persist state.

Installing this skill should mainly affect how code explanations are formatted. Users should expect analogies, ASCII diagrams, and step-by-step explanations, and may want language-preference clarification if they do not want Chinese-oriented responses.

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
  • 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
91% confidence
Finding

The skill description is broadly scoped to common activities like explaining code, teaching a codebase, or answering how something works, which can cause it to activate for many ordinary developer requests. Overly broad activation increases the chance of unintended routing, response-style hijacking, or interference with other more appropriate skills, especially in multi-skill environments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill content and description enforce Chinese-language behavior without indicating that this restriction is required or allowing user language preference to override it. This can degrade usability, cause confusion, and create prompt-routing or policy conflicts when the user expects another language, making the skill behave unexpectedly in normal interactions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.