The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external data from Slack channels and blog posts to generate its output, creating a surface for indirect prompt injection.
Ingestion points: Slack search results (slack_search_public_and_private), Slack thread content (slack_read_thread), and external blog excerpts from orbitant.com/en/insights/.
Boundary markers: Absent. The instructions do not provide explicit delimiters or warnings to the agent to disregard instructions contained within the fetched messages.
Capability inventory: The skill has access to Slack search and read tools. It does not possess capabilities for shell execution, file system modification, or general network requests beyond the specified Slack and blog domains.
Sanitization: Absent. The content is interpolated directly into the newsletter draft generation process.

orbitant-newsletter