ClawHub
Back to skill

Security audit

Insurance Agent — Coverage-Gap Premortem

Security checks for vulnerabilities and agentic risk

Overview

This is a small insurance coverage-review prompt skill with no executable code, persistence, credential access, or hidden behavior.

Install only if you want agents to apply a worst-case coverage-gap review lens during actual insurance coverage decisions. Users should still verify policy language and jurisdiction-specific requirements with qualified professionals, and avoid treating this skill as legal or binding coverage advice.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation description uses broad phrases such as 'placing or reviewing coverage' and 'policy review,' which can match many ordinary insurance conversations and cause the skill to trigger outside a narrowly scoped premortem scenario. Over-activation is risky here because the skill steers agents toward coverage-gap and E&O framing, which may distort routine interactions or introduce unnecessary recommendations and documentation burdens.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The markdown guidance says to activate when 'placing or reviewing coverage' and not activate when 'no coverage decision in play,' but that still leaves substantial ambiguity because many ordinary insurance review activities involve some level of coverage discussion without needing a formal premortem. In this context, ambiguous triggering can cause the agent to invoke this skill too broadly, potentially biasing advice toward worst-case gap analysis in situations where a simpler workflow would be more appropriate.

Static analysis

No suspicious patterns detected.