Security audit

RedHat Frontend Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward frontend app builder with one metadata quality issue but no evidence of hidden, destructive, or credential-stealing behavior.

Before installing, ask the publisher to replace the malformed trigger metadata with explicit supported triggers. The skill otherwise appears appropriate for users who want an agent to create and modify frontend project files and run normal validation commands.

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: 97% confidence
Finding: The triggers field is populated with System.Object[], which is not a valid concrete trigger definition and leaves activation behavior undefined or parser-dependent. Ambiguous trigger configuration can cause the skill to be invoked unexpectedly, bypass intended usage constraints, or fail open in systems that apply permissive defaults.
Content: No source excerpt is available for this finding.