The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions guiding the agent's reasoning process. It does not include any executable scripts, commands, or tool usage.
[SAFE]: The frontmatter configuration explicitly disables model invocation, which restricts the skill's ability to call external tools or models, thereby limiting its execution environment to basic reasoning.
[SAFE]: No patterns of prompt injection, data exfiltration, obfuscation, or persistence mechanisms were identified during the analysis.

melech-challenge