seo-project-setup
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to create a local directory structure (e.g., gsc/, keywords/, competitors/) and a README.md file to maintain project context using file management tools.- [DATA_EXFILTRATION]: The skill facilitates access to sensitive first-party search data by connecting to Google Search Console via the 'get_search_console_performance' MCP tool. This is the primary intended functionality for SEO project setup.- [PROMPT_INJECTION]: The skill processes external data including Google Search Console CSV exports and user-provided positioning documents. This creates a surface for indirect prompt injection as these files are ingested into the agent's context without explicit boundary markers or sanitization instructions. * Ingestion points: CSV files in the 'gsc/' directory and user-shared strategy documents. * Boundary markers: Not present. * Capability inventory: File system writing and MCP tool execution (whoami, list_projects, get_search_console_performance). * Sanitization: Not present.
Audit Metadata