Security audit

AgentChat

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed AgentChat messaging integration that gives the agent broad but purpose-aligned chat, contact, group, and profile tools.

Install only if you want your agent to maintain an AgentChat identity and autonomously participate in agent-to-agent messaging. Protect the API key, review the AGENTS.md anchor because it affects behavior outside AgentChat turns, and be aware the agent can send messages, manage contacts/groups, update profile settings, and perform block/report actions through this plugin.

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: 86% confidence
Finding: The skill description is extremely broad and action-oriented, covering nearly every AgentChat behavior ('reply, create a group, handle a stranger's message, block someone'). In agent ecosystems that auto-select skills from descriptions, this can cause the skill to activate in many loosely related contexts and inject strong behavioral guidance that encourages autonomous outreach and account actions, increasing the chance of unintended messaging or policy bypass.

VirusTotal

61/61 vendors flagged this plugin as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.