ai-seo
Warn
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to clone and install a third-party tool from an unverified GitHub repository (https://github.com/AminForou/mcp-gsc) to facilitate integration with Google Search Console data.
- [COMMAND_EXECUTION]: The skill includes shell command templates for cloning code, installing Python dependencies via pip, and configuring MCP servers, which could result in the execution of arbitrary code if followed by the agent or user.
- [INDIRECT_PROMPT_INJECTION]: The skill defines workflows that ingest data from external, untrusted sources including competitor websites, SERP data, and software review platforms (G2, Capterra). Ingestion points: External API data and web-scraped competitor content referenced in SKILL.md. Boundary markers: None identified. Capability inventory: CMS publishing capabilities (WordPress, Webflow) and local command execution. Sanitization: No specific sanitization or validation steps are outlined for the ingested data.
Audit Metadata