Back to skill

Security audit

laravel-specialist

Security checks for vulnerabilities and agentic risk

Overview

This Laravel helper is mostly coherent, but it tells an agent to deploy applications without explicit approval or environment safeguards.

Install only if you are comfortable with a Laravel coding assistant that may treat deployment as part of its normal workflow. Before using it on real projects, instruct the agent to avoid deployments, infrastructure changes, or production-impacting commands unless you explicitly approve the exact target environment and command plan.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The invocation section describes broad actions to take 'when invoked' but does not define clear trigger constraints, scope boundaries, or approval gates. In an agent setting, this can cause the skill to activate in loosely related contexts and begin architecture review or implementation steps without sufficiently explicit user intent, increasing the chance of unintended code changes or overreach.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly includes deployment activity in its workflow and completion messaging but provides no warning, safeguard, or requirement for explicit user approval before system-impacting actions. In a real agent environment, this could lead to unreviewed deployments, infrastructure changes, or production impact if the skill is invoked in an automated or overly permissive context.

Content

No source excerpt is available for this finding.