Agently Mail

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed mail-management skill that uses an external CLI and OAuth to access email, with confirmation required for write actions.

Install only if you want an agent to access and operate an Agently/QQ Mail mailbox through the Tencent QQMail CLI. Expect OAuth credentials to be stored locally, and review message summaries carefully before confirming any send, reply, forward, or trash action. For general email advice or discussion, avoid invoking the skill unless you actually want mailbox access.

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: 92% confidence
Finding: The skill description says it should be used for 'any mail-related operation,' which is broad enough to be triggered by ordinary conversation about email rather than an explicit request to access or modify a mailbox. In a skill that can read, send, forward, delete mail, and perform OAuth login, over-broad activation increases the chance of unintended tool use and exposure of sensitive mailbox data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal