glim.sh

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward connector to a paid hosted live-data MCP service, with the main caution being that tool calls go to an external provider.

Install only if you are comfortable sending search queries, fetched URLs, and related tool-call metadata to Glim for processing and billing. Avoid using it with secrets, private company URLs, personal data, or sensitive research unless you have approved the provider's privacy and billing terms. Consider limiting enabled tools with the documented tools parameter and prefer scoped MCP configuration where your client supports it.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill instructs users to connect a hosted MCP server and route searches, fetches, and other live-data requests through a third-party endpoint, but it does not clearly warn that prompts, tool arguments, queries, and retrieved content may be transmitted to and processed by that external service. This creates a real data exposure risk because agents may send sensitive research topics, proprietary URLs, internal identifiers, or other confidential context to the provider without the user making an informed trust decision.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal