EngageLab App Push

• Outcome: Review
• Latest audit: May 29, 2026, 9:29 PM
• Version:
  1.0.1

Overview

This is a coherent EngageLab push-notification API helper, but it can perform real account-level sends, recalls, schedules, and irreversible user deletion without strong built-in confirmation guidance.

Install only if you control the EngageLab application and want an agent to help prepare or call its push APIs. Before any live send, recall, schedule change, tag/alias mutation, or user deletion, confirm the exact app, audience, identifiers, message content, and consequences; use validation/read-only calls first where possible, protect the Master Secret, and require HMAC verification for callbacks in production.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger list includes broad terms such as 'push notification', 'tag alias', and 'push statistics', which can match many ordinary requests beyond this specific vendor integration. Overbroad activation increases the chance the skill is invoked in contexts where the user did not intend to use EngageLab, causing accidental external API usage or credential solicitation.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill advertises destructive and privacy-impacting operations like deleting users, modifying tags/aliases, scheduling pushes, and recalling messages without consistently requiring explicit user-facing warnings or confirmation. In practice, this could lead to unintended deletion of device/user records or changes to messaging state that affect end users and compliance obligations.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The documentation explicitly describes callback verification as optional even though the endpoint accepts inbound POSTs that influence business analytics and event processing. If implementers skip signature validation, an attacker can forge callback requests to inject fake delivery or click events, poison metrics, trigger downstream automation, or abuse any business logic tied to callback processing.

VirusTotal

65/65 vendors flagged this skill as clean.