Edvisage Agent Connect

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only coordination skill with disclosed handoff and shared-context templates, not executable code or hidden automation.

Safe to install as a coordination template. Use it only with trusted agents, keep shared context files minimal, avoid secrets or regulated data in handoffs/logs, and remember the free version does not actually enforce trust verification or automated routing.

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
This markdown file describes what the skill does but never states how or when it should be invoked, nor any constraints or negative examples for use. For a coordination skill with broad concepts like delegation and context sharing, the lack of explicit trigger phrases or boundaries could cause unintended activation in ordinary collaboration-related conversations.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal