The Agent Skills Directory

[SAFE]: The skill defines a standard development workflow with explicit security considerations.
[DATA_EXFILTRATION]: The instructions include a defensive rule for the agent: "Sensitive variables should not appear in the final response." This mitigates the risk of accidental credential or secret exposure during environment configuration.
[COMMAND_EXECUTION]: The skill utilizes the apifox CLI tool to manage API resources. This is consistent with the vendor's purpose and is documented as a requirement in the metadata.
[PROMPT_INJECTION]: The skill facilitates the processing of external data which constitutes a surface for indirect prompt injection.
Ingestion points: SKILL.md (Workflow includes importing from codebases, PRD documents, demand documents, and OpenAPI/Postman specifications).
Boundary markers: None explicitly defined in this file; the workflow relies on subsequent tool-specific skills.
Capability inventory: apifox CLI (Permissions to design endpoints, write schemas, and manage environment variables).
Sanitization: No specific sanitization logic is described; however, the agent is instructed to use endpoint get to verify the structure and content of saved assets, which serves as a validation step.

apifox-workflow-api-lifecycle