The Agent Skills Directory

[SAFE]: The skill consists of purely instructional content and architectural best practices for system instrumentation. It does not perform any network operations, file system modifications, or code execution.
[DATA_EXPOSURE]: The instructions include proactive security measures, specifically mandating that secrets, tokens, and PII must never be logged and recommending the use of a PII scrubber.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided service inventories and path definitions to generate a plan. While this represents a data ingestion surface, the risk is negligible as the skill functions as a static knowledge guide for planning rather than a runtime execution engine for untrusted data.

observability-stack