The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions utilize npx to download and execute the @useclawlink/cli package from the NPM registry. This package is the primary tool for authenticating and communicating with the Zoom API through the vendor's infrastructure.
[COMMAND_EXECUTION]: The skill operates by executing shell commands via the ClawLink CLI. This includes administrative tasks like login and connect, as well as operational tasks like list_meetings or create_whiteboard.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to read data from external sources (Zoom meetings, recordings, and whiteboards) and process it within the agent context. This creates a surface for indirect prompt injection if an attacker-controlled meeting or recording contains malicious instructions.
Ingestion points: zoom_list_meetings, zoom_get_a_meeting, zoom_get_meeting_recordings, and zoom_list_whiteboards in SKILL.md.
Boundary markers: The skill provides a procedural boundary by instructing the agent to "Reads first; confirm with the user before any write."
Capability inventory: The skill possesses the ability to execute shell commands and modify Zoom account data through the CLI.
Sanitization: No explicit sanitization or filtering of the ingested Zoom data is mentioned in the skill instructions.

zoom