ClawHub
Back to skill

Security audit

Notifly: Sending Notifications

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly scoped Notifly notification-sending workflow with explicit preview and confirmation before any real message is sent.

Install only if you want the agent to operate Notifly notification workflows. Before approving a send, check the preview carefully because the skill says the notification is real and cannot be recalled; vague requests should be clarified before confirmation.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger examples are broad enough to match generic user requests such as 'notify this user' or 'trigger a notification,' which increases the chance the skill is invoked in situations the user did not specifically intend for this capability. Because this skill performs a real external side effect, overly loose routing can lead to accidental initiation of a notification-send workflow and unnecessary exposure to confirmation prompts or mistaken sends if the surrounding agent mishandles confirmation state.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.