ai-seo
Warn
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation instructs the user to clone a repository from an unverified third-party account on GitHub (AminForou/mcp-gsc) and install its dependencies using pip. This source is not associated with a trusted organization or the skill author.
- [REMOTE_CODE_EXECUTION]: The provided instructions for setting up the Google Search Console (GSC) MCP server involve executing a Python script (server.py) retrieved from the aforementioned unverified GitHub repository.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted sources including competitor websites, G2/Capterra reviews, and SEO tool APIs (DataForSEO, Semrush). The instructions lack explicit boundary markers or sanitization requirements for this external content. Ingestion points: external competitor data, user reviews, and SERP APIs. Capability inventory: subprocess execution for MCP setup, content generation workflows (AirOps). Boundary markers: absent. Sanitization: absent. This creates a surface where malicious instructions embedded in the external content could potentially influence the agent's behavior.
Audit Metadata