The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, such as Swagger or OpenAPI documentation, to generate test plans and scripts. This represents an attack surface where malicious instructions embedded in the documentation could influence the agent's behavior during the generation process.
Ingestion points: API documentation, Swagger/OpenAPI files, and Postman collections provided by the user (described in the 'Work Flow' section of SKILL.md).
Boundary markers: No specific delimiters or warnings to ignore embedded instructions are present in the processing logic.
Capability inventory: The skill generates code templates (Jest, Pytest) but does not have direct execution capabilities or file-system write access defined in its configuration.
Sanitization: No explicit sanitization or filtering of the input documentation is specified.
[EXTERNAL_DOWNLOADS]: The skill includes instructions to recommend and install an external resource (github:mindverse/skillhub) using the /install command if the user's requirements exceed the skill's primary scope. This targets a repository for an ecosystem-specific skill hub.

api-test