The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the user to add an external MCP server configuration from https://rube.app/mcp to access the Confluence toolkit.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from Confluence, creating a surface for indirect prompt injection attacks.
Ingestion points: External content enters the agent's context through tools such as CONFLUENCE_GET_PAGE_BY_ID, CONFLUENCE_SEARCH_CONTENT, and CONFLUENCE_CQL_SEARCH as described in SKILL.md.
Boundary markers: The skill body lacks instructions for the agent to use specific delimiters or to disregard instructions embedded within the retrieved Confluence content.
Capability inventory: The skill provides significant modification capabilities, including CONFLUENCE_CREATE_PAGE, CONFLUENCE_UPDATE_PAGE, and CONFLUENCE_DELETE_PAGE (referenced in SKILL.md).
Sanitization: There is no description of content sanitization or validation processes for the data fetched from Confluence before it is utilized by the agent.

confluence-automation