The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest and process untrusted external data including OpenAPI/AsyncAPI specifications, code comments, and annotations (SKILL.md). * Ingestion points: The skill identifies API scope and scope specifications, and uses automated updates from code comments (SKILL.md). * Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the documentation source files. * Capability inventory: The skill possesses high-impact capabilities including automated testing of documentation examples, multi-language SDK generation, and CI/CD pipeline integration for automated releases (SKILL.md). * Sanitization: The instructions do not define any validation or sanitization steps for the external specifications or code snippets before they are processed or tested.

api-documenter