Delay, Deny, Defend

• Outcome: Pass
• Latest audit: Jun 15, 2026 at 10:48 AM UTC
• Version:
  1.0.0

Overview

This is a text-only insurance-claims guidance skill with some broad onboarding triggers, but no hidden execution, data access, or persistence.

Before installing, understand that this skill provides opinionated consumer guidance about insurance companies and may activate during broad insurance-rights or onboarding questions. Treat it as educational support, verify current state-specific rules, and consult a qualified professional for significant claims or legal decisions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

High

• Confidence: 98% confidence
• Finding: This manifest text defines invocation conditions that are not specific to the insurance-claims domain and could match many unrelated conversations. The lack of clear constraints or exclusion conditions makes unintended activation likely.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: This phrasing does not define when the skill should or should not activate, leaving invocation to subjective interpretation. In a markdown skill description, this kind of open-ended trigger guidance can cause accidental invocation outside the intended context.

VirusTotal

64/64 vendors flagged this skill as clean.