research-logger

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it says: research a topic, optionally find a GIF, and save the result as a local or Bear note.

Install this only if you are comfortable sending research topics to Brave and possibly Giphy when API keys are configured, and with generated notes being saved locally or in Bear. Avoid confidential topics unless those provider and storage behaviors are acceptable, and verify grizzly, curl, python3, and the notes template are available.

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: 93% confidence
Finding: The skill declares no explicit permissions, yet its own description and usage clearly rely on web research, content fetching, GIF lookup, and invoking the `grizzly` CLI, which implies network access, shell execution, and likely environment/tool access. This mismatch weakens trust boundaries and reviewability because consumers may approve the skill believing it is lower-privilege than it actually is, increasing the chance of unintended data access or command execution in an agent context.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal