The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown files providing reasoning frameworks. No malicious code, prompt injections, or unauthorized data access patterns were identified. The core functionality is limited to structured dialogue and reasoning guidance using the Socratic method and other analytical frameworks.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied positions and proposals for critique, representing a data ingestion surface in SKILL.md. It incorporates a structured confirmation loop (steelmanning) as a boundary marker to ensure the agent's interpretation is validated by the user. The skill possesses no dangerous capabilities, such as file system writing, network operations, or arbitrary command execution, and relies on inherent model reasoning for safe content handling.

the-fool