Security audit

Keyword Research from Search Console - SEOmatic

Security checks for vulnerabilities and agentic risk

Overview

This SEO keyword-research skill is purpose-aligned and disclosed, with user approval required before any site changes go live.

Install this only if you intend to connect SEOmatic to your site data. Review the OAuth/API-key permissions and any paid-credit usage, and only approve staged SEOmatic tasks when you want those specific site changes to run.

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: Line L003 says to use the skill when the user asks for "keyword research, keyword ideas, what to write about, search volume, or a keyword strategy." Phrases like "what to write about" and "keyword ideas" are broad and could match everyday content-planning requests without clearly limiting when this skill should or should not activate.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.