The Agent Skills Directory

[No Code] (SAFE): The skill is composed solely of markdown instructions and metadata, with no scripts or binaries provided, which significantly reduces the attack surface.
[Command Execution] (SAFE): The skill requests access to the Bash tool, which is necessary and expected for a backend testing utility; no malicious shell commands are present in the documentation.
[Prompt Integrity] (SAFE): The instructions are direct and consistent with the skill's stated purpose, with no evidence of prompt injection or attempts to bypass agent safety filters.
[Indirect Prompt Injection] (SAFE): While the skill is designed to ingest and process user code, it does not include instructions that would facilitate the execution of hidden commands within that code, and it lacks sensitive capability tiers that would elevate the risk.

backend-test