search-console
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'seo' package from the official npm registry ('npm i -g seo') and recommends using an MCP server hosted at 'seoskill.dev'. These are standard procedures for utilizing the CLI tool around which the skill is built.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of search queries and page titles retrieved from Google Search Console.
- Ingestion points: Data enters the agent context through the 'seo report', 'seo page', and 'seo data' commands, as well as local CSV file reads from the 'gsc/' directory.
- Boundary markers: The instructions emphasize reporting data as facts in tables and naming capped or missing data before interpretation, which provides a structural boundary for the output.
- Capability inventory: The skill uses the 'seo' CLI to perform network operations (Google API calls) and file system reads (CSV exports).
- Sanitization: While the skill does not explicitly detail sanitization of search queries, it focuses on quantitative analysis and reporting within defined heuristics, which naturally limits the impact of potential injection within the search data itself.
Audit Metadata