ClawHub
Back to skill

Security audit

garage-door-safety-audit

Security checks for vulnerabilities and agentic risk

Overview

This local garage-door checklist has proportionate access, but its reporting bugs and generic safety advice require care.

Use this as a recordkeeping and estimation aid, not proof that a door is safe. Check actual test history because resolved failures remain listed and untested doors can show no open issues. Follow your opener's manual for testing and adjustments: [Chamberlain's guidance](https://support.chamberlaingroup.com/s/article/How-do-I-test-the-Safety-Reversal-System-1484145519301) specifies monthly reversal tests with a board rather than a towel. Treat spring-life dates as estimates and leave dangerous repairs to a qualified technician.

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
  • 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: file_read, 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.

Status reports historical failures as open safety issues even after passing retests.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The status calculation collects failing results but never clears them when a subsequent passing retest exists, contradicting its claim to show issues with 'no passing retest since.' In a physical-safety audit, persistent false alarms can cause unnecessary servicing and alarm fatigue, undermining trust in genuine hazard warnings; this is a reporting-integrity defect rather than evidence of malicious behavior.

Content

No source excerpt is available for this finding.