The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes run_command to execute npx @redocly/cli lint, which involves fetching the Redocly CLI package from the npm registry at runtime.
[COMMAND_EXECUTION]: The skill is configured to use the run_command tool to perform API validation and linting, which is a standard part of its primary functionality as an API designer.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it ingests untrusted data from the user's local codebase and has powerful capabilities to write files and execute commands.
Ingestion points: The skill uses read_file and grep to analyze existing API code, route definitions, and middleware.
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from being influenced by malicious instructions contained within the analyzed source files.
Capability inventory: The skill possesses file-writing capabilities (rewrite_file, edit_file, create_file_or_folder) and command execution capabilities (run_command).
Sanitization: No sanitization or validation of the ingested file content is performed prior to the agent processing it.

api-designer