Back to skill

Security audit

hotel-room-safeguard

Security checks for vulnerabilities and agentic risk

Overview

This skill provides hotel inspection checklists and local evidence logs, but its camera checks should not be treated as proof that a room is surveillance-free.

Use this as a manual checklist, not a camera detector or safety guarantee. Protect or delete local travel logs when no longer needed, and review generated letters before sharing them.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The manifest promises hidden-camera RF/emission checks, but the camera checklist provides only visual inspection and optional network-observation guidance.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

The skill description promises hidden-camera RF/emission checks, but the implemented checklist offers visual inspection and optional network observation without RF detection procedures or equipment requirements. In a privacy-protection skill, this capability mismatch can create false confidence that the advertised checks were completed, leaving concealed recording devices undetected. This is a safety-relevant coverage gap, not evidence of malicious behavior or a software-execution vulnerability.

Content

No source excerpt is available for this finding.