The Agent Skills Directory

[SAFE]: The skill's primary function is formatting text based on predefined templates. It uses standard Markdown and Notion-specific structures (callouts, toggles, tables).
[DATA_EXPOSURE]: The skill mentions optional integration with Notion via Model Context Protocol (MCP) tools such as API-post-page and API-patch-block-children. These are standard tool invocations for the platform and do not involve hardcoded credentials or unauthorized data exfiltration.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided content (an ingestion point for potential indirect injection), it includes guardrails such as requiring user confirmation before saving to Notion and checking for existing pages to prevent accidental overwrites. The transformation is purely structural and does not execute the processed content.
[DYNAMIC_CONTEXT_INJECTION]: No use of the !command syntax or silent shell executions was found in the skill manifest.
[OBFUSCATION]: Analysis of the text and scripts revealed no hidden URLs, Base64 encoding, zero-width characters, or homoglyph-based attacks.

notion-format