gsc-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from Google Search Console, including search queries and page metadata which are controlled by external parties.\n
- Ingestion points: Data enters the system via GSC MCP tools and is processed through JSON and CSV files.\n
- Boundary markers: The instructions lack specific delimiters or warnings to ignore instructions that might be embedded in the search data.\n
- Capability inventory: The skill employs a Python script for data processing and permits the agent to write output files to the project directory.\n
- Sanitization: While the script validates and normalizes SEO metrics, it does not perform sanitization on text-based search queries.\n- [EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository (
AminForou/mcp-gsc) as a required tool for live data integration.
Audit Metadata