The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute the hurl command-line utility for running tests and generating reports. This includes constructing shell commands to process test files and pass dynamic variables.
[EXTERNAL_DOWNLOADS]: The documentation directs users to install the hurl tool via well-known and trusted package management systems such as Homebrew, Winget, and APT.
[DATA_EXFILTRATION]: The skill manages authentication tokens and merchant identifiers, prescribing their storage in local environment files. It includes a specific warning to use .gitignore to prevent these secrets from being exposed in version control.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its automated ingestion of external data. Ingestion points include API documentation from Apifox MCP and project source code (Java Param/VO/Mapper files). The skill currently lacks explicit boundary markers or sanitization logic for data extracted from these sources before it is used to generate executable test scripts and bug reports.
[SAFE]: The skill's operations are transparent and aligned with its stated objective of API automation. No obfuscation, persistence mechanisms, or unauthorized privilege escalations were found.

auto-test