ClawHub
Back to skill

Security audit

Ads Creator Selector

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only advertising planning skill with minor naming and trigger-scope issues, but no hidden execution, persistence, credential use, or data exfiltration behavior.

Installers should be aware that this skill may trigger on broad advertising and growth prompts, and the publisher should align the slug, display name, and skill name. There is no evidence it runs code, accesses accounts, stores data, or changes ad platforms automatically.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger section is broad enough to match many generic business, marketing, and growth conversations, not just requests specifically needing creator/KOL selection. This can cause unintended invocation of the skill, leading the agent to apply overly specialized ad-planning behavior in contexts where it is not appropriate, which may degrade decision quality or override better-matched skills.

Description-Behavior Mismatch

Low
Confidence
95% confidence
Finding
The manifest identity is inconsistent with the provided skill context: the metadata uses the slug/display name for an 'Ads Creator Selector' / 'kohl-creator-selector' variant while the declared skill name is 'kol-creator-selector'. Identity mismatches can cause operator confusion, incorrect deployment or review decisions, and may help a malicious or poorly reviewed skill masquerade as a different capability, though this file alone does not show direct code execution or privilege abuse.