The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from X (Twitter), such as tweets, user bios, and community posts, which are untrusted external sources. This content could contain malicious instructions intended to manipulate the agent's behavior in subsequent steps.\n
Ingestion points: Data is retrieved from the Xquik API via endpoints such as GET /x/tweets, GET /x/users, and GET /events (SKILL.md).\n
Boundary markers: The skill does not provide specific instructions or delimiters to isolate untrusted content or warn the agent to ignore embedded commands within the scraped data.\n
Capability inventory: The skill facilitates network operations using the fetch API to communicate with Xquik. It does not include file system access or shell command execution capabilities.\n
Sanitization: There are no instructions for sanitizing or validating the text data extracted from X before it is used by the agent or passed to related skills like social-content.\n- [NO_CODE]: The skill consists entirely of documentation, guidelines, and code snippets within SKILL.md. It does not include or execute any standalone script files, binaries, or automated installation commands.

x-twitter-scraper