Security audit

Java Spring Boot

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Spring Boot guidance skill with minor documentation and validation-quality issues, but no hidden or unsafe agent behavior.

Install only if you want a broad Spring Boot coding helper that can read, write, and run shell commands in your project. Review generated security code before use, especially CSRF settings, and treat the included validator as a convenience check rather than a strict release gate.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Note

Location: scripts/validate.py:113
Finding: Configuration Validation Failure Is Ignored by the Final Exit Status
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The declared purpose is about Spring Boot application development capabilities, but the supplied code does not implement or support Spring Boot app building features such as REST APIs, security, data access, or actuator setup. Instead, it performs repository/skill validation tasks: checking for SKILL.md, required directories, and config.yaml contents. This is a materially different primary purpose from the description, so it should be flagged as a mismatch.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill provides a Spring Security example that disables CSRF globally without explaining that this is only appropriate for strictly stateless, non-browser-based APIs. Users may copy this configuration into cookie-based or browser-accessible applications, which can expose state-changing endpoints to cross-site request forgery attacks.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: This markdown file documents how to invoke the skill, so SQP-1 applies. The pattern claude "java-spring-boot - [your task description]" shows a broad free-form trigger format but does not define boundaries, exclusions, or negative examples, making it unclear what requests should or should not activate the skill.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.