Clarity Research

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it says: query Clarity Protocol protein-variant data, with an optional API key for higher rate limits.

Install only if you are comfortable with research queries going to clarityprotocol.io. If you enable higher rate limits, use a dedicated CLARITY_API_KEY and do not store unrelated secrets under that environment variable.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 89% confidence
Finding: The skill documentation indicates use of both network access and an environment variable (`CLARITY_API_KEY`), but the skill does not declare corresponding permissions. Undeclared capabilities reduce transparency and can lead to users or hosting platforms granting trust without realizing the skill can exfiltrate environment data or make outbound requests, even if the described use case appears legitimate.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal