The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the getnote command-line utility to perform searches, list knowledge bases, and retrieve specific note contents. This is the intended behavior for interacting with the vendor's service.
[PROMPT_INJECTION]: The skill processes untrusted data from user notes which could potentially contain malicious instructions intended to influence the AI agent.
Ingestion points: Note titles and content retrieved from getnote search and getnote note as referenced in SKILL.md.
Boundary markers: Absent. There are no instructions or delimiters provided to help the agent distinguish between its system prompt and data retrieved from notes.
Capability inventory: The skill uses the getnote CLI in SKILL.md for read operations and search queries.
Sanitization: Absent. Content from notes is interpolated directly into the agent's context without escaping or filtering.

getnote-search