Back to skill

Security audit

App Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed app-building guidance skill that may lead an agent to scaffold, modify, test, and deploy apps, but its instructions fit that purpose and include user confirmation checkpoints.

Install this if you want broad app-building help. Review plans before approving implementation or deployment, especially when a request involves dependency installation, external services, databases, payments, or production deployment.

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
96% confidence
Finding

The skill description is broad enough to match a wide range of common software requests, which can cause the agent to invoke this powerful app-building skill in contexts where a narrower, safer, or more specialized skill would be more appropriate. Over-broad routing increases the chance of unintended code generation, project modification, or deployment actions from ambiguous prompts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The keyword matrix uses highly generic terms such as 'api', 'backend', 'service', 'dashboard', and 'plugin', which are common in ordinary discussion and can trigger this skill for unrelated or underspecified requests. Because the skill is positioned to scaffold, modify, test, and deploy applications, weak keyword matching can lead to misrouting and unnecessary high-impact actions.

Content

No source excerpt is available for this finding.