VerdictSwarm

Security checks across malware telemetry and agentic risk

Overview

VerdictSwarm is a coherent crypto token analysis skill that uses a disclosed external API, with privacy and dependency-review cautions but no artifact-backed malicious behavior.

Install only if you are comfortable sending token identifiers, chain choices, and scan context to VerdictSwarm's external service. Review the external MCP package before installing it with pip, and treat the risk scores as decision support rather than authorization for automatic trades or payments.

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: 88% confidence
Finding: The trigger phrases are very broad and likely to fire during ordinary crypto discussion, not just when a user explicitly wants this third-party skill invoked. That can cause unexpected activation of a network-enabled skill and unnecessary transmission of token identifiers or trading-related queries to an external service.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill instructs the agent to use MCP tools or call the API directly for token analysis, but it does not clearly warn that token addresses, chain selections, and related query context will be transmitted to api.vswarm.io. This creates a privacy and consent issue because users may believe analysis is local when it is actually performed by a third party.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal