ClawHub
Back to skill

Security audit

Ad Platform Tracker Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only ad platform tracking skill whose external research and scraping guidance matches its stated purpose, though users should apply normal legal and platform-policy caution.

Before installing, be aware that live competitor monitoring may use third-party scraping or automation services. Prefer official APIs and transparency tools, confirm platform terms and applicable law, protect any API tokens, and verify time-sensitive ad policy claims because the static notes are dated early 2026.

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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s trigger conditions are extremely broad and include language like 'always use this skill' plus a wide set of loosely related requests. This creates an overreach risk where the agent may invoke external tracking/scraping behavior for many ad, policy, competitor, or compliance questions that could have been answered more safely or with narrower tool use, increasing exposure to untrusted data and policy-unsafe actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs use of scraping tools for competitor ads and platform monitoring without warning about legal, terms-of-service, privacy, or account-enforcement risks. In a competitive intelligence context, this omission can lead the agent to collect data in ways that violate platform restrictions or create compliance issues for users who may not understand the associated risks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.