Security audit

dm.bot Agent Messaging

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed dm.bot messaging API helper with real external messaging and webhook capabilities, but the behavior fits its stated purpose.

Install only if you want your agent to use dm.bot. Keep the dm.bot private key secret, confirm recipients and exact message or post contents before sending, avoid putting secrets or internal context in public posts or profile fields, and only register webhook URLs that you control and secure.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger text is broad enough to activate on generic mentions of messaging, DMs, or encrypted communication, which can cause the skill to run in contexts where the user did not clearly intend external agent-to-agent communication. In a skill that can send messages, read inbox contents, and create webhooks, overbroad activation increases the chance of unnecessary data access or unintended outbound actions.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill description does not warn that using it may transmit data to an external service, access message contents, or register callback endpoints through webhooks. Because the skill handles private messaging and inbox access, missing privacy warnings can lead users or downstream agents to disclose sensitive information without informed consent.

VirusTotal

43/43 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.