The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides detailed instructions for the agent to utilize the apifox CLI tool to perform operations such as creating, updating, and running complex test scenarios.
[INDIRECT_PROMPT_INJECTION]: The skill describes workflows that ingest data from external sources, which constitutes a potential surface for indirect prompt injection. However, this is an inherent characteristic of the tool's primary purpose for API testing.
Ingestion points: Data is pulled from external API response bodies ({{$.1.response.body.token}}), headers, and database query results as described in SKILL.md.
Boundary markers: The skill utilizes standard variable interpolation delimiters ({{...}}) to separate data from instructions.
Capability inventory: The skill possesses the capability to perform network requests, execute database operations, and run JavaScript logic (customScript) via the Apifox CLI, as detailed in the instructions.
Sanitization: The instructions do not explicitly detail sanitization or validation of the ingested external data before it is interpolated into subsequent requests or scripts.
[REMOTE_CODE_EXECUTION]: The skill documentation includes guidance on implementing runtime logic using JavaScript (pm.test and customScript) within the Apifox execution environment. This is the intended functionality for modeling business logic and assertions in test scenarios.

apifox-test-scenario