The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external system performance data, such as API response bodies and system metrics, to generate performance reports. It possesses capabilities to perform network operations and write files, creating a potential surface for instructions embedded in external data to influence the agent.
Ingestion points: Processes data from external systems via k6 HTTP requests (e.g., loginResponse.json(), apiResponse.json()) and general performance monitoring inputs.
Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when processing external data.
Capability inventory: Performs network requests using the k6/http module and writes report files (performance-report.json, performance-summary.html) via the handleSummary function in SKILL.md.
Sanitization: No explicit sanitization, validation, or filtering of external content is described before the data is interpolated into analysis reports.

performance-benchmarker