The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external, untrusted news sources which could contain adversarial instructions intended to influence the agent's behavior.
Ingestion points: External data is retrieved using the google_news_bulk_articles, tavily_search, and exa_search tools as listed in SKILL.md.
Boundary markers: The workflow does not include instructions to use delimiters or to treat tool outputs as untrusted information.
Capability inventory: The skill uses sandbase_call_tool to access external web content.
Sanitization: There are no instructions to sanitize, escape, or filter the content retrieved from search results before it is processed.

news-aggregator