The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted user note content.\n- Ingestion points: Note content is ingested via read_blocks and read_note tools as described in SKILL.md.\n- Boundary markers: There are no explicit instructions to use boundary markers or delimiters when interpolating note content into the prompt.\n- Capability inventory: The skill possesses write capabilities through the edit_block tool.\n- Sanitization: No sanitization or validation of note content is prescribed before processing.

tag-organize