The Agent Skills Directory

[SAFE]: The skill's logic is dedicated to educational review and self-testing. It uses standard platform tools to read note content and provide feedback without attempting to access unauthorized system resources or external domains.
[SAFE]: Data access is limited to the user's note repository through high-level API functions. There are no mechanisms for data exfiltration or unauthorized credential usage.
[PROMPT_INJECTION]: The skill processes untrusted user-provided content (notes), which serves as a potential surface for indirect prompt injection. However, the risk is negligible as the skill lacks high-impact capabilities like network access or shell execution. Ingestion points: the agent reads note content using read_note, read_blocks, and search_note_content as defined in SKILL.md. Boundary markers: the instructions do not include specific delimiters or guidelines for the agent to ignore instructions embedded within the notes. Capability inventory: the skill can modify and sync notes using create_note, edit_block, and sync_note. Sanitization: no explicit validation or filtering logic is mentioned for content read from the notes.

note-review-coach