The Agent Skills Directory

[SAFE]: The skill instructions define a benign analytical workflow for problem-solving. No evidence of prompt injection, data exfiltration, or malicious behavior was found. The instructions remain within the boundaries of a standard cognitive assistant task.\n- [NO_CODE]: The skill consists entirely of markdown-based system instructions and does not include or reference any external scripts, binaries, or software packages. This significantly reduces the attack surface as there is no mechanism for executing code or establishing remote connections.

brainstorm