The Agent Skills Directory

[SAFE]: The skill enforces a human-in-the-loop process by requiring a 'yes' from the user before applying any changes to a connected notes application. It also prevents data loss by instructing the agent to preserve original text alongside rewrites and to archive instead of delete by default.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data as it processes user-supplied 'captures' from pasted text or inbox folders. Ingestion points: User-provided text strings or existing note files. Boundary markers: The instructions do not specify the use of delimiters for separating instructions from user data. Capability inventory: The skill has the ability to read folders and perform file operations (move, rename, edit) via connected tools. Sanitization: There is no explicit sanitization of the input data. However, the requirement for user review of the triage plan effectively mitigates the risk of the agent performing unauthorized actions due to instructions hidden within the notes.

inbox-triage