Back to skill

Security audit

Insurance Agent Intelligent Trainer

Security checks for vulnerabilities and agentic risk

Overview

The skill was rated benign because the scanners found no reported executable scripts or major security concerns, but flagged a scope issue: generic training phrases can activate insurance coaching for unrelated requests.

Consider whether you’re comfortable with generic training or assessment requests potentially being routed into insurance coaching. The verdict is benign, but confidence is medium, and Skillspector’s analysis was partial because two local references could not be resolved.

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
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)

Generic training and assessment phrases trigger activation without an insurance-context requirement.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The instruction to immediately activate on generic phrases such as 'skill assessment' and 'daily training plan' does not require an insurance context, allowing unrelated requests to be diverted into insurance coaching. The insurance-specific metadata reduces ambiguity, but the unconditional activation rule still creates a scope-control weakness; no privileged operations or external data transfers are specified, so the demonstrated impact is limited to workflow disruption and irrelevant responses.

Content

No source excerpt is available for this finding.