Back to skill

Security audit

Visionos Spatial Engineer

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow visionOS expertise skill with no install steps, executables, persistence, credential use, or hidden high-impact behavior.

Install only if you want visionOS spatial engineering guidance. The main caveat is that its activation wording is generic, so users should invoke it for visionOS-related tasks rather than unrelated development work.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation text is broad enough that an orchestrator or user could invoke this skill in unintended contexts simply by referring to its specialty, which increases the chance of accidental routing or prompt-triggered activation. While the content is not overtly malicious, ambiguous invocation rules can weaken control boundaries between skills and make misuse easier in multi-agent systems.

Content

No source excerpt is available for this finding.