Claim

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only claims guidance skill that does not request system access, but users should verify legal and insurance advice before acting.

Safe to install from an agent-security perspective. Treat it as drafting and organization support, not legal advice: avoid sharing unnecessary sensitive documents or personal details, and verify deadlines, policy terms, local procedures, and legal strategy with official sources or a qualified professional for denied, injury, employment, high-value, or urgent claims.

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: 89% confidence
Finding: The trigger description is very broad and can activate for many ordinary compensation, dispute, or payment-related questions that may not actually require this specialized skill. Over-invocation can steer users into legal/claims-style guidance inappropriately, increasing the chance of irrelevant or overly assertive advice in sensitive insurance, employment, or injury contexts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal