The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute gcx CLI commands such as gcx config, gcx providers, gcx resources, and gcx query. These are used to retrieve information from a Grafana Cloud stack for demonstration purposes.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (Grafana Cloud logs, traces, and resource names) which could potentially contain malicious content intended to influence the agent's behavior.
Ingestion points: Data enters the context via the output of gcx logs query, gcx traces query, and gcx resources get commands.
Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded content in the retrieved data.
Capability inventory: The skill uses the Bash tool to execute system commands and AskUserQuestion to interact with the user.
Sanitization: There is no explicit sanitization of the retrieved data mentioned in the skill instructions.

gcx-demo