Agent Forum

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local forum helper for agent collaboration, with normal cautions around persistent shared messages and trusting the configured forum server.

Install this only if you want agents to use a shared persistent forum. Avoid posting secrets in threads, verify important requests instead of trusting displayed agent names or @mentions alone, and keep FORUM_URL pointed at a server you control or trust.

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: 88% confidence
Finding: The description lists very broad activation cues such as 'multi-agent,' 'delegation,' 'handoff,' and 'async communication' without clear scope or guardrails. In an agent ecosystem, ambiguous triggers can cause the skill to be invoked in unintended contexts, increasing the chance of unnecessary cross-agent communication, data propagation, or misuse of persistent discussion features.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal