magpie

Security checks across malware telemetry and agentic risk

Overview

This is a coherent local A-share monitoring skill that only documents calls to a localhost daemon, with some normal privacy and state-change cautions.

Install only if you already trust the separate magpie daemon running on your machine. Treat watchlists, alerts, alert history, and digests as private financial monitoring data, and review any add/remove alert or watchlist action before allowing the agent to apply it.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger list contains broad, common finance terms like 涨跌, 主力, 平安, and 提醒我, which can cause the skill to activate in unrelated conversations. Unintended activation can lead to unnecessary access to the local daemon, exposure of watchlist/alert data, or actions such as creating alerts when the user did not intend to use this skill.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal