The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns such as prompt injection, obfuscation, or persistence mechanisms were detected in the skill definition.
[COMMAND_EXECUTION] (LOW): The skill facilitates the execution of local scripts using bun run and interacts with tmux for layout management. This is expected behavior for terminal UI components and does not pose a security risk.
[INDIRECT_PROMPT_INJECTION] (LOW): As a toolkit for displaying data, the skill ingests external information for rendering in TUIs (e.g., calendar slots, document text). This is a standard operational surface for UI-focused skills.
Ingestion points: The --config CLI parameter and parameters for the pickMeetingTime, editDocument, and bookFlight API functions.
Boundary markers: Not explicitly mentioned in the documentation; the system relies on the underlying code for input handling.
Capability inventory: Local process execution via bun and tmux, and inter-process communication via Unix sockets.
Sanitization: Not documented at this level of the API.

canvas