The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches real-time news articles and market signals from the vendor's API at ai.6551.io. This communication is necessary for the skill's primary functionality.
[COMMAND_EXECUTION]: Utilizes curl to perform network requests and jq to parse and format JSON data, which are standard utilities for this type of task.
[PROMPT_INJECTION]: The skill processes news headlines and summaries from an external source, creating a surface for indirect prompt injection where malicious content could attempt to influence the agent.
Ingestion points: Data retrieved from the /open/news_search endpoint as described in SKILL.md.
Boundary markers: None; the skill does not use specific markers to delimit untrusted news data from agent instructions.
Capability inventory: The skill has the ability to execute system commands via the exec tool.
Sanitization: The skill does not implement sanitization or filtering of the incoming news text before it enters the agent's context.

opennews