Security audit

MVP Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a simple MVP planning skill with no executable code, privileged access, persistence, or hidden data handling.

Installers should expect the skill to push toward very small, fast-launch MVP decisions, including charging early and using existing tools; review whether that opinionated startup framework matches the conversations where you want it active.

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger keywords and read-when conditions are broad enough to activate on many ordinary product-planning conversations, not just clear requests for this specific MVP framework. Over-triggering can cause the agent to inject premature business or payment-oriented advice into unrelated contexts, reducing reliability and potentially steering users away from their actual intent.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.