demo

Security checks across malware telemetry and agentic risk

Overview

This is a simple document-summary skill that only formats user-provided text into a structured Markdown summary.

This skill is appropriate for summarizing text you intentionally provide. Avoid giving it confidential documents unless you are comfortable with your agent processing that content, and review summaries for accuracy before relying on them.

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's invocation guidance is overly broad because it triggers on generic requests like summarizing documents, analyzing text, or extracting key points. This can cause the skill to activate in many unrelated contexts, increasing the chance it is selected when a more appropriate or safer skill should handle the request, which can lead to unintended processing or prompt-scope confusion.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal