The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external articles and images on X (Twitter).
Ingestion points: Content is fetched from x.com via the read_x_article.py script and agent-provided web extraction tools as described in SKILL.md.
Boundary markers: The instructions lack specific delimiters or explicit warnings to the model to ignore potential instructions embedded within the fetched article text.
Capability inventory: The skill utilizes network tools to fetch HTML and vision tools to analyze images extracted from the articles.
Sanitization: There is no implementation of sanitization or filtering for the fetched content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill perform network requests to x.com, twitter.com, and pbs.twimg.com to retrieve article content and associated media. These domains are well-known services associated with the Twitter/X platform.

read-x-articles