Claude

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only document analysis skill with clear limits and no evidence of hidden access, code execution, persistence, or data exfiltration.

Safe to install as a document-reasoning helper. Use it for summaries, issue spotting, structure improvements, and comparisons, but do not rely on it as legal, tax, compliance, procurement, or contract-approval authority. Be careful before pasting confidential business or legal documents into any AI environment, and verify the publisher if you expected an official Claude or Anthropic offering.

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 activation trigger "long documents" is overly broad and can cause this skill to be selected for many unrelated requests that merely involve lengthy text, even when the user does not want legal/commercial reasoning. In an agentic system, overly permissive routing can lead to inappropriate handling of user tasks, reduced safety from bypassing more suitable skills, and misleading outputs in higher-stakes contexts.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal