The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references the papaparse utility from jslib.k6.io, which is the official repository for k6 extensions. It also suggests using official GitHub Actions from the grafana organization for automating performance tests in CI pipelines. These represent well-known and established service endpoints.
[INDIRECT_PROMPT_INJECTION]: The skill operates by taking user-supplied parameters (such as endpoints, test types, and thresholds) and inserting them into predefined script templates.
Ingestion points: System descriptions and performance requirements provided by the user, as defined in the 'Trigger' section of SKILL.md.
Boundary markers: The skill uses markdown code blocks to separate generated scripts from instructional text.
Capability inventory: The generated output consists of scripts intended for execution by load testing engines, which naturally possess network communication and local file read capabilities (e.g., in SKILL.md and references/k6-scripting.md).
Sanitization: The skill relies on the structural format of the templates and does not explicitly describe input sanitization routines for the interpolated values.
[DYNAMIC_EXECUTION]: The skill's primary function is to dynamically construct JavaScript and Python test scripts by merging user-provided configuration with internal code templates, which is expected behavior for a code-generation utility.

backend-load-testing