The Agent Skills Directory

[COMMAND_EXECUTION]: The skill operates primarily through the agent-react-devtools CLI. It executes subcommands to manage a local daemon (start, stop) and query runtime data from connected applications. These operations are consistent with the skill's stated purpose of providing a developer tool interface.- [EXTERNAL_DOWNLOADS]: The documentation in references/setup.md suggests using npx agent-react-devtools init for automated framework configuration. This involves downloading and executing the vendor's package from a registry. As agent-react-devtools is a resource belonging to the author 'piotrski', this is documented as a standard vendor-provided setup process.- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by ingesting and displaying data (component names, props, and state) from external React applications.
Ingestion points: Data enters the agent's context through CLI commands like agent-react-devtools get tree and agent-react-devtools get component.
Boundary markers: The instructions do not specify the use of delimiters or protective headers for the data returned by these commands.
Capability inventory: The agent has the Bash capability to execute local commands via the tool.
Sanitization: There is no mention of sanitizing or escaping the retrieved component properties or state values before they are processed by the agent.

react-devtools