The Agent Skills Directory

[SAFE]: The skill serves as a technical reference for developers. All external links point to official documentation for Slack, Vercel, and the Chat SDK framework, which are well-known and trusted services. There are no instructions to download external scripts, execute untrusted code, or access sensitive system files.
[INDIRECT_PROMPT_INJECTION]: The skill establishes patterns for handling untrusted data from the Slack Events API. It includes security best practices for sanitizing this data before output.
Ingestion points: The skill ingest data via Slack Events API payloads such as app_mention and message.im, as detailed in references/slack-inbound-message-formats.md.
Boundary markers: While it does not specify prompt delimiters, it provides rigid routing logic in references/slack-thread-routing.md to distinguish between mentions and passive message monitoring.
Capability inventory: The skill leverages Slack Web API methods for message posting and assistant thread management (e.g., assistant.threads.setStatus).
Sanitization: Explicit instructions are provided in references/slack-output-formatting.md to escape dynamic text (&, <, and >) to prevent rendering issues or injection in the Slack client interface.

slack-development