kml

Security checks across malware telemetry and agentic risk

Overview

This is a read-only KML/KMZ inspection skill with no evidence of hidden network access, credential use, persistence, or destructive behavior.

Safe for normal KML/KMZ inspection. Only use it on files you are comfortable having summarized in the conversation, because KML/KMZ files can contain private place names and precise location data.

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: 90% confidence
Finding: The skill enables implicit invocation, which allows the agent to trigger it without an explicit user request. Because the activation scope is only loosely described and not narrowly constrained in policy, the skill may be invoked in contexts where the user did not intend KML/KMZ processing, potentially causing unintended file handling or data exposure through over-broad tool use.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal