Free Generator Text

Security checks across malware telemetry and agentic risk

Overview

The skill appears aimed at remote generation/editing, but it may connect to a backend and route ambiguous requests into authenticated edit actions too automatically.

Review this before installing. Use it only if you are comfortable with a remote service receiving generation/edit requests and uploaded content. Look for a clear consent step before backend connection, token/session creation, and any edit request; avoid sending private files until that behavior is explicit and scoped.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The routing table sends essentially all unmatched prompts to the SSE generation/edit path, which can cause unintended network actions and backend-side edits from ambiguous or incidental user input. In a skill that uploads content and issues authenticated API calls, such a broad fallback increases the chance of overbroad action execution without explicit user confirmation.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly instructs automatic connection to a remote backend on first open, including token acquisition and session creation, without clear opt-in or a meaningful warning that network requests, token handling, and persistent session state will occur. This creates a privacy and consent problem because the user may trigger external authentication and session establishment merely by opening the skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal