Risk Guardian

Security checks across malware telemetry and agentic risk

Overview

This Paradex risk-analysis skill is coherent and instruction-only, with the main caveat that some trigger phrases are broad for a financial-account context.

Install this if you want Paradex risk reports and margin-health analysis. Before use, confirm the Paradex MCP connection has only the permissions you intend, and be aware that generic safety questions could activate the skill unless the trigger wording is tightened.

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 (1)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger text is broad enough to match generic phrases like "am I safe", "should I be worried", or other common risk/safety questions that may be unrelated to Paradex. This can cause the skill to activate outside its intended scope, pulling account-risk workflows into unrelated conversations and potentially exposing sensitive financial context or producing confusing, domain-inappropriate responses.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal