Jupiter Quote

Security checks across malware telemetry and agentic risk

Overview

This appears to be an unfinished placeholder skill, not a dangerous one.

Install only if you are comfortable with this being a placeholder. It does not appear to contain harmful behavior, but it also does not currently provide the advertised Jupiter quote capability.

SkillSpector

By NVIDIA

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

Confidence: 95% confidence
Finding: The manifest description is still placeholder text and does not define when the skill should activate or what tasks it is intended to handle. In an agent environment, vague activation scope can cause the wrong skill to be invoked, leading to unsafe or unintended behavior, especially if the skill later gains scripts or privileged operations.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The Overview section is unfinished and provides no concrete operational guidance, leaving the skill’s scope and expected usage ambiguous. This increases the chance of misapplication by an agent or user, which can become a security issue when unclear instructions interact with automation, external tools, or sensitive workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal