ClawHub
Back to skill

Security audit

Sending Notifications

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Notifly notification sender with clear confirmation safeguards before any real notification is sent.

Before installing, understand that this skill can send real Notifly notifications after you confirm a preview. Review the workflow, recipients or topic, payload, and environment carefully because the skill states sent notifications cannot be recalled.

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
94% confidence
Finding

The skill advertises broad trigger phrases such as 'trigger a notification', 'notify this user', and 'send this to a topic', which can overlap with ordinary conversational requests and increase the chance the agent invokes a real-world sending capability unexpectedly. Although the skill includes a two-step confirmation flow that reduces the chance of silent execution, overbroad routing still creates risk of unintended activation for a dangerous action.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.