The Agent Skills Directory

[COMMAND_EXECUTION]: The skill operates by executing a local Node.js script (lov-plane-cli.mjs) to interact with the Plane API. Additionally, the AGENTS.md file contains instructions suggesting the agent use JXA (JavaScript for Automation) to export Apple Reminders, which would involve the execution of shell commands such as osascript if the agent follows these guidelines.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external sources, which creates a surface for indirect prompt injection. Ingestion points: The skill reads task names, descriptions, and comments from the Plane API instance. It also suggests reading from Apple Reminders. Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external data as distinct from instructions. Capability inventory: The agent can execute the provided CLI tool, which has network access and can perform write/delete operations on the Plane instance. Sanitization: There is no evidence of sanitization or filtering of retrieved content before it is processed by the agent.

lov-plane-cli