The Agent Skills Directory

[COMMAND_EXECUTION]: Executes local commands find and ls to search for route files and existing documentation. It also runs postman spec lint to validate the generated specification. These commands are necessary for the skill's primary function.
[EXTERNAL_DOWNLOADS]: Mentions the postman-cli utility. The agent suggests installation via the npm registry if it is not present. This is a trusted dependency associated with the skill's author and targets a well-known service.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes codebase files. Ingestion points: Local source code files (JS, TS, PY, GO, JAVA, RB) and existing OpenAPI specs. Boundary markers: Absent. Capability inventory: File system write (postman/specs/openapi.yaml) and shell command execution. Sanitization: No explicit sanitization of codebase content is mentioned before it is processed by the agent.

generate-spec