The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent. * Ingestion points: The agent retrieves external content using x timeline, x search, and x mentions (SKILL.md). * Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between data and instructions within the retrieved content. * Capability inventory: The agent has the ability to perform actions such as x tweet, x delete, and x follow (SKILL.md). * Sanitization: No sanitization or validation steps are provided for the data retrieved from the X API.
[COMMAND_EXECUTION]: The skill is built around interacting with the x command-line utility. * The instructions provide various command patterns for the agent to execute in a shell environment to manage social media activities.

x-cli