QMD CLI

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent markdown-search helper, but users should be careful about what local notes they index and trust the external qmd CLI before installing it.

Install only if you trust the qmd project, prefer a pinned release or reviewed package when possible, and index only folders you are comfortable making searchable by your agent. Use the MCP server only with trusted clients and avoid full-document or all-match retrieval on highly sensitive notes unless you intend that content to enter the conversation.

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: 93% confidence
Finding: The skill explicitly states that `query` uses LLM re-ranking, but the description and usage guidance do not warn that user queries and potentially retrieved document snippets may be sent to an external model or service. In a local markdown search tool, users may reasonably assume all operations remain local, so the missing disclosure can lead to unintended exposure of sensitive notes, documentation, or transcripts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal