Back to skill

Security audit

Pilot Priority Queue

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Pilot Protocol priority-message helper, with one disclosed manual clear command users should treat carefully.

Install only if you already use Pilot Protocol and understand pilotctl behavior. Review inbox contents before using the clear command, because clearing a priority inbox may remove messages you still need.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documented pilotctl --json inbox --clear command is destructive because it deletes queued messages after processing, yet the skill provides no explicit warning, confirmation step, or guidance on safe use. In a priority-queue context, accidental clearing can cause irreversible message loss, missed urgent alerts, and SLA violations, making the omission security-relevant even though it is not overtly malicious.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.