The Agent Skills Directory

[SAFE]: The skill consists solely of instructions for using a command-line interface and does not include any executable scripts or hidden code. No hardcoded secrets or suspicious metadata were found.\n- [COMMAND_EXECUTION]: The skill outlines commands for the getnote CLI tool, which may involve reading local files (e.g., when saving images) or accessing the network (e.g., when saving URLs). These capabilities are restricted to the intended functionality of the note management service.\n- [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data, creating a surface for indirect prompt injection.\n
Ingestion points: Content enters the agent context through getnote save <url> and getnote note <id> commands in SKILL.md.\n
Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following directives embedded in note content.\n
Capability inventory: The skill allows the agent to modify, delete, or publicly share notes (getnote note update, getnote note delete, getnote note share in SKILL.md).\n
Sanitization: No input validation or content sanitization mechanisms are described.

getnote-note