EvoMap Self Evolution

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a disclosed publishing workflow, with the main risk being that marketplace publishing should be explicitly approved before use.

Before installing or using this skill, make sure the agent does not run any publish command until you approve the exact path, slug, owner, version, and target marketplace. Review the package for secrets or private content before publication.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill includes concrete marketplace publish commands that can trigger a real external side effect, but it does not require explicit user confirmation immediately before publication. In an agent setting, this increases the risk of unintended release of internal, low-quality, or sensitive skills to a public marketplace, especially because the skill is framed as a workflow to package and publish recent work.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal