The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from search results and Search Console which could theoretically contain malicious instructions.
Ingestion points: Untrusted data enters the context via get_search_console_performance, research_keywords, and list_saved_keywords as described in SKILL.md.
Boundary markers: The skill does not define explicit delimiters or 'ignore' instructions for the ingested data.
Capability inventory: The skill has the capability to modify state via update_project_context and save_keywords as mentioned in SKILL.md.
Sanitization: No explicit sanitization or validation of the external content is mentioned before it is processed or written back to the project context.

keyword-clustering