ClawHub
Back to skill

Security audit

scheduler notification runbook

Security checks for vulnerabilities and agentic risk

Overview

This is a focused scheduling guidance skill; its webhook advice deserves caution but is disclosed and tied to explicit user intent.

Before enabling webhook delivery, confirm the destination is intended, trusted, authenticated, and HTTPS-protected, and send only the minimum reminder or run-result content needed. For ordinary reminders, prefer the simpler systemEvent or announce delivery patterns described by the skill.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill recommends delivery.mode = "webhook" for external HTTP delivery but does not instruct the operator to warn the user, minimize transmitted data, or verify that sending reminder contents or run results to a third-party endpoint is intended. In a scheduling/runbook skill, that omission can lead to accidental exfiltration of sensitive chat content, task details, or derived summaries to external services under the guise of normal notification setup.

Content

No source excerpt is available for this finding.