The Agent Skills Directory

[SAFE]: No security threats or malicious behaviors were detected in the skill's code or documentation.
[PROMPT_INJECTION]: Instructions focus on routing logic and cost optimization. No evidence of instructions that attempt to bypass safety filters or override agent constraints.
[DATA_EXFILTRATION]: No network operations, sensitive file path access, or credential hardcoded secrets were detected.
[EXTERNAL_DOWNLOADS]: The skill does not perform remote downloads. The 'pytest' dependency is a standard testing tool.
[COMMAND_EXECUTION]: No usage of subprocesses, shell commands, or privilege escalation techniques was found.

model-hierarchy