ClawHub
Back to skill

Security audit

Pilot Announce

Security checks for vulnerabilities and agentic risk

Overview

This is a small communication helper that tells agents how to send Pilot Protocol announcements, with no bundled code or hidden persistence.

Install only if you already use and trust the Pilot Protocol environment. Do not treat the documented workflow as proof of receipt or acknowledgment unless pilotctl separately provides a verified receipt-status command, and avoid sending secrets or sensitive incident details without confirming transport and logging protections.

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

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises read receipts and acknowledgment tracking, but the documented commands only send, publish, subscribe, and read inbox contents; they never show any mechanism to retrieve or verify delivery or acknowledgment state. This can mislead operators into believing critical announcements were received when no confirmation exists, creating an integrity and operational security risk during urgent updates or incident response.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs users to broadcast announcement text and target multiple peers over the Pilot Protocol network without warning that message contents, recipient identifiers, and metadata will be transmitted and potentially logged. In practice, users may send sensitive security or policy announcements assuming the operation is low-risk, which can expose internal information or communication patterns if the network, endpoints, or logs are not adequately protected.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.