The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches instrumentation references and SDK schemas from Grafana's official GitHub repository via https://raw.githubusercontent.com/grafana/agento11y/main/llms.txt. This is a trusted source provided by the vendor.
[COMMAND_EXECUTION]: The skill uses the gcx CLI via Bash to manage Grafana Cloud contexts, list stacks, and verify that telemetry data has been successfully ingested into the platform.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and interprets remote content to guide its code modification and execution behavior.
Ingestion points: Remote content is retrieved using WebFetch from llms.txt as defined in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the fetched content.
Capability inventory: The skill has access to Edit, Write, and Bash tools, allowing it to perform file modifications and command execution based on the external input.
Sanitization: There is no explicit validation or sanitization of the fetched remote content before it influences the agent's actions.

agento11y-instrument