The Agent Skills Directory

[SAFE]: The skill serves as a documentation and instruction set for an agent to interact with Google Search Console via legitimate CLI tools or Model Context Protocol (MCP) servers. It follows standard practices for configuration and data analysis.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, specifically Google Search Console search queries and page metadata, which could theoretically contain adversarial content intended to influence the agent.
Ingestion points: Data output from the gws CLI tool or the mcp-server-gsc tool (SKILL.md).
Boundary markers: No specific boundary markers or "ignore instructions" delimiters are defined for the tool output processing.
Capability inventory: The skill is configured to use the Bash and Read tools for executing commands and reading data.
Sanitization: No explicit sanitization, filtering, or validation of the external GSC data is mentioned in the instructions.

30x-seo-monitor