The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of local diagnostic scripts via Node.js (perf_inspect.mjs) and makes extensive use of the WP-CLI toolset (wp doctor, wp profile) to interact with the WordPress environment.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, creating a potential vulnerability surface.
Ingestion points: Untrusted data enters the agent context through the outputs of WP-CLI commands, server logs, and REST API response headers and bodies (documented in SKILL.md).
Boundary markers: The instructions do not define explicit delimiters or warnings to ignore embedded instructions within the processed performance data.
Capability inventory: The agent is granted the ability to execute shell commands and interact with the file system via WP-CLI and Node.js (documented in SKILL.md).
Sanitization: There is no specified sanitization or filtering for the external data before it is interpolated into the agent's workflow.
[DYNAMIC_EXECUTION]: The skill utilizes the wp profile eval command, which allows for the runtime execution of PHP code snippets to profile specific code paths. While a standard feature of the profiling tool, it represents a dynamic execution surface.
[EXTERNAL_DOWNLOADS]: The skill references technical documentation from WordPress's official domain (make.wordpress.org), which is a well-known and trusted service for development guidelines.

wp-performance