The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to fetch and synthesize data from external Notion pages and potentially third-party integrations like Slack, Google Drive, GitHub, and Jira. This creates a surface area for indirect prompt injection where malicious instructions inside those external documents could theoretically influence the agent's behavior during synthesis.
Ingestion points: The skill uses Notion:notion-fetch and Notion:notion-search to pull content into the agent's context.
Boundary markers: The templates provided for reports (e.g., in reference/research-summary-template.md) do not explicitly define delimiters or instructions to ignore embedded commands in the source text.
Capability inventory: The agent has the capability to write new pages to the workspace using Notion:notion-create-pages.
Sanitization: No explicit sanitization or filtering of retrieved content is mandated in the provided workflow.
[NO_CODE]: The skill consists entirely of Markdown-based instructions, reference documentation, and JSON-based evaluation scenarios. It does not include any executable scripts (e.g., Python or Node.js), which eliminates risks associated with remote code execution or traditional shell-based privilege escalation.

notion-research-documentation