The Agent Skills Directory

[SAFE]: The skill contains no executable code, remote dependencies, or network operations. It consists entirely of instructions and a report template used to evaluate other AI agent configurations.
[SAFE]: While the skill represents an indirect prompt injection surface by requesting that the user provide untrusted data (prompt text, workflow descriptions, and agent configurations) for analysis in the 'Usage' section, it possesses no exploitable capabilities. There are no subprocess calls, file operations, or network tools available in the skill that could be targeted by instructions embedded in the analyzed data.

diagnose