ClawHub
Back to skill

Security audit

Ads Incident Tickets

Security checks for vulnerabilities and agentic risk

Overview

This is a simple ads incident triage skill with a somewhat broad trigger list but no hidden execution, persistence, credential use, or automatic account changes.

Install only if you want help formatting and routing ad operations incidents. Because the trigger wording is broad, users should make sure it is being used for actual ad incident triage and review any recommended containment actions, ticket payloads, and owner contact details before acting on them.

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
96% confidence
Finding

The trigger section is broad enough to match many ordinary marketing or business-performance questions, not just ad incident triage. That can cause unintended invocation of this skill in contexts where the user did not request incident management, leading to irrelevant routing, over-collection of operational data, or incorrect escalation-oriented guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.