The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from untrusted external sources, specifically email messages, calendar events, and contact details, which could contain malicious instructions.
Ingestion points: The skill retrieves external content using tools such as OUTLOOK_SEARCH_MESSAGES, OUTLOOK_GET_MESSAGE, and OUTLOOK_GET_EVENT (SKILL.md).
Boundary markers: The instructions lack delimiters or specific directives to help the agent distinguish between its system instructions and the untrusted content being processed.
Capability inventory: The skill possesses write-access capabilities including creating contacts (OUTLOOK_CREATE_CONTACT) and mail folders (OUTLOOK_CREATE_MAIL_FOLDER).
Sanitization: No sanitization, filtering, or validation of the external content is prescribed before the agent processes the data.
[EXTERNAL_DOWNLOADS]: The skill requires the user to configure a connection to an external third-party MCP server endpoint.
Evidence: The 'Setup' section in SKILL.md instructs the user to add https://rube.app/mcp as an MCP server in their client configuration. This external endpoint is responsible for searching tools and managing connections.

outlook-automation