ClawHub
Back to skill

Security audit

Ads Q&A Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown ads Q&A guide with no code, persistence, credential access, or automatic account-changing behavior.

Before installing, understand that this skill may activate for broad marketing or growth questions; users should provide clear ad-platform, campaign, and KPI context and review any recommendations before applying them in real ad accounts.

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

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The activation section mixes broad business outcomes like growing revenue, profit, or optimizing budgets with the stated purpose of rapid ads Q&A and triage. That mismatch creates ambiguity about when the skill should activate, making it easier for the agent to route general business strategy questions into an execution-oriented ads workflow that may produce overconfident or mis-scoped recommendations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords are broad enough to match many ordinary business or marketing discussions, which can cause unintended skill invocation outside the narrow ads-Q&A use case. In an agent system, overbroad activation increases the chance that this skill handles requests it was not designed for, leading to irrelevant guidance, incorrect downstream handoffs, or bypass of more appropriate skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.