Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Security audit
insurance-gap-auditor
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent local insurance checklist tool, with the main caution that policy details are saved in a local JSON file when you use the inventory feature.
Install only if you are comfortable entering insurance limits, deductibles, net worth, and income into a local file. Treat the generated policies.json as sensitive household financial information and delete or protect it if you use a shared or backed-up machine.
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
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The script persists insurance policy details, coverage limits, deductibles, and related financial information to a local JSON file without any notice, consent prompt, or protective controls. On shared machines or insecure environments, this can expose sensitive household financial/insurance data to other local users, backups, or malware, and the skill context increases sensitivity because the stored data directly reflects assets, liability limits, and coverage gaps.
- Content