The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions and metadata. No scripts, binaries, or executable code components are included in the skill package.
[SAFE]: No malicious patterns, data exfiltration attempts, or injection vulnerabilities were detected. The skill defines a logical framework for evaluating tasks and recommending model parameters without executing external commands or accessing sensitive data.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided task descriptions to generate recommendations, it has no exploitable capabilities. The instructions explicitly prohibit executing the tasks being sized, changing configuration, or calling other models, effectively neutralizing potential injection attacks within this scope.

modelchk