Back to skill

Security audit

Vibe Coding Workflow

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed workflow guide for AI-assisted software development, with no hidden execution, credential access, persistence, or unrelated data handling.

Install this if you want a structured, phased coding workflow. Be aware it may activate for broad build or debugging requests and add process overhead, so use explicit wording when you do or do not want the workflow.

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
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrase at this location is broad enough that normal user requests about building something 'step by step' could invoke the skill unintentionally. Unintended invocation can steer conversations into a prescribed workflow the user did not explicitly request, causing incorrect routing, confusion, or over-application of the skill in unrelated coding contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The phrase 'I have a bug I can't fix' is a common everyday support request and is too vague to uniquely indicate this specific workflow skill. Because debugging is a broad domain, this trigger may capture many unrelated troubleshooting requests and force an unnecessary workflow entry point, reducing accuracy and potentially interfering with more appropriate skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description uses very broad trigger phrases such as 'help me build a project step by step', 'asks how to start a new feature or project with AI', and 'encounters bugs they can't resolve', which overlap with a large fraction of general software-assistance requests. This can cause the skill to activate outside its intended niche, increasing prompt-surface exposure and making it easier for this workflow to override or interfere with more appropriate, narrower skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.