ClawHub
Back to skill

Security audit

Pilot Email Bridge

Security checks for vulnerabilities and agentic risk

Overview

This email bridge is coherent and user-directed, but users should treat relays and cleanup commands carefully because email data may be sent out or deleted.

Install only if you already use Pilot Protocol and trust the SMTP or webhook relay you configure. Prefer HTTPS endpoints, minimize sensitive email content and attachments, protect email credentials outside the skill, and avoid pilotctl inbox --clear unless you have confirmed the messages are no longer needed.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill shows webhook setup and message publishing that route email content to external endpoints, including recipient, subject, and body data, without any privacy, trust-boundary, or transport-security warning. Because this skill is explicitly for bridging agent messages to email workflows, operators may transmit sensitive operational data to third-party relays or over insecure HTTP without recognizing the exposure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The example includes pilotctl --json inbox --clear, which appears to delete or clear inbox contents, but the documentation provides no warning that messages may be removed irreversibly. In an automation/agent skill context, users may copy-paste commands directly, so this omission materially increases the chance of accidental data loss or destruction of evidence.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.