Security audit

fullstack-developer

Security checks for vulnerabilities and agentic risk

Overview

This is a broad full-stack development guidance skill with no bundled code, hidden execution, persistence, or unrelated data handling.

Installers should treat this as a general full-stack development helper and keep normal review controls around auth, database migrations, CI/CD, and deployment changes, since those areas can affect production systems even though the skill itself does not add hidden capabilities.

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

Confidence: 89% confidence
Finding: The skill's invocation guidance is broad and underspecified, allowing it to be engaged for almost any 'fullstack' task without clear boundaries, prerequisites, or safety gates. In a multi-agent system, this can cause overbroad activation, unnecessary access to context across backend, frontend, and auth layers, and increased chance of unsafe changes being proposed or performed outside the intended scope.

Static analysis

No suspicious patterns detected.