The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to install the sports-skills package using pip, potentially from a GitHub repository (https://github.com/machina-sports/sports-skills.git). This repository is maintained by the skill author, machina-sports.
[COMMAND_EXECUTION]: The skill operates primarily through a command-line interface (sports-skills). It provides the agent with shell commands to retrieve data, which are executed in the local environment.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from the Nevobo API, including news headlines, tournament descriptions, and match results. This creates a potential vulnerability if the external API returns malicious instructions designed to influence the agent's output.
Ingestion points: Commands such as get_news, get_tournaments, and get_results described in references/api-reference.md fetch content from the api.nevobo.nl domain.
Boundary markers: The skill instructions do not specify the use of delimiters or provide instructions to the agent to ignore commands embedded in the retrieved external data.
Capability inventory: The skill has the ability to execute shell commands via the sports-skills CLI and make network requests to the Nevobo API.
Sanitization: There is no evidence of sanitization, filtering, or validation of the text data returned by the API before it is processed by the agent.

volleyball-data