The Agent Skills Directory

[SAFE]: Extensive analysis of the skill's instructions, templates, and examples reveals no malicious patterns. The skill adheres to its stated purpose and uses official Notion integration tools for all operations.
[PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection as it processes content from external sources (Notion pages, and potentially connected apps like Slack or Jira) to generate reports. This is a characteristic of research-oriented skills and is handled within the scope of intended functionality. * Ingestion points: Data enters the context via Notion:notion-fetch as described in SKILL.md and the examples/ directory. * Boundary markers: The skill utilizes structured markdown templates (e.g., reference/comparison-template.md) which provide natural sections, but no specific adversarial boundary markers are enforced. * Capability inventory: The skill possesses the ability to search, read, and write content within Notion using the provided tools. * Sanitization: No programmatic sanitization of ingested content is specified; the skill relies on the model's ability to distinguish between data and instructions during synthesis.

notion-research-documentation