The Agent Skills Directory

[SAFE]: The skill is composed of markdown instructions and templates for organizing meeting information. It does not contain any executable scripts, binaries, or unauthorized network configurations. All operations are performed using standard Notion tools (search, fetch, create-pages) for their intended purpose.- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection because it fetches and processes content from Notion pages which may contain untrusted data. Ingestion points: Content is retrieved from the Notion workspace using the Notion:notion-fetch tool as described in the workflow in SKILL.md. Boundary markers: There are no explicit boundary markers or delimiters defined to separate untrusted Notion content from the system prompt, although the instructions tell the agent to distinguish facts from research. Capability inventory: The skill has write access to the workspace via Notion:notion-create-pages and Notion:notion-create-comment. Sanitization: No sanitization or validation steps are included for the content fetched from Notion before it is used by the agent.

notion-meeting-intelligence