The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and procedural guidelines for a behavioral psychologist persona. It contains no executable code, remote script downloads, or command-line operations. The instructions do not attempt to bypass safety filters or access sensitive local files like credentials or SSH keys.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for ingesting user-provided data (e.g., Target Human profiles, business objectives) to design onboarding flows. However, this surface is assessed as safe because the skill lacks any high-risk capabilities, such as shell execution, file writing, or network access, that could be exploited via malicious data.
Ingestion points: The "CONTEXT GATHERING" section in SKILL.md identifies Target Human profile, Objective, and Constraints as external data inputs.
Boundary markers: None explicitly defined.
Capability inventory: None; the skill is limited to generating descriptive text output based on the provided framework.
Sanitization: None identified.

onboarding-psychologist