ClawHub
Back to skill

Security audit

Pilot Verify

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documented Pilot Protocol verification guide that uses expected pilotctl read-only checks and does not install code, persist changes, or hide privileged behavior.

Before installing, confirm you already trust the pilotctl binary and Pilot Protocol daemon because this skill relies on them. Treat the local info command as optional context, and use a dedicated daemon-status workflow if you are troubleshooting the local daemon itself.

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 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest explicitly says this skill should not be used for verifying local daemon status and directs users to pilotctl info instead. However, the skill's own 'Essential Commands' includes pilotctl --json info as a documented operation, which broadens the skill beyond remote agent verification into local daemon inspection.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.