The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest and process data from external Slack conversations, which may contain hidden or malicious instructions meant to influence the agent's behavior.
Ingestion points: The skill uses SLACK_SEARCH_MESSAGES, SLACK_FETCH_MESSAGE_THREAD_FROM_A_CONVERSATION, and SLACK_FETCH_CONVERSATION_HISTORY as described in SKILL.md to retrieve message content.
Boundary markers: No specific delimiters or instructions to treat external message content as untrusted are present in the skill instructions.
Capability inventory: The agent has significant capabilities to interact with the workspace, including sending and scheduling messages (SLACK_SEND_MESSAGE, SLACK_SCHEDULE_MESSAGE) and retrieving channel information.
Sanitization: There is no mention of content filtering, escaping, or sanitization of the Slack messages before they are processed by the agent.
[EXTERNAL_DOWNLOADS]: The setup instructions require connecting to a remote MCP server located at https://rube.app/mcp, which is an external dependency for the skill's operation.

slack-automation