Back to skill

Security audit

baby-nap-navigator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed offline baby nap scheduling aid that stores caregiver-entered timing data locally and does not show hidden network, credential, or privilege behavior.

Before installing, understand that caregiver-entered baby sleep data is saved locally in a JSON file. Use the default state file or a dedicated path, avoid pointing --state at important files, and treat the output as scheduling help rather than medical advice.

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 (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill documentation describes local file read/write behavior via a persistent JSON state file, but it does not declare any explicit tool scope such as permissions or allowed-tools. Even though the stated behavior is limited and appears offline-only, undeclared filesystem access weakens least-privilege guarantees and can cause the agent runtime to grant broader file capabilities than reviewers expect.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.