The Agent Skills Directory

[SAFE]: The skill contains standard natural language instructions to establish a specific AI persona (technical advisor). It does not attempt to bypass safety filters or override core system instructions.
[SAFE]: There are no external downloads, remote scripts, or package dependencies identified. The skill operates entirely within the provided markdown text.
[SAFE]: The skill configuration explicitly disables model invocation (disable-model-invocation: true), which prevents the agent from calling external tools and eliminates the primary attack surface for indirect prompt injection or data exfiltration.

challenge-me