The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown-based guidelines, examples, and reference material. No scripts, binaries, or command execution patterns were found in the provided files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided arguments (ingestion point). While this involves processing untrusted data, the risk is non-existent because the skill possesses no tools or capabilities—such as network access, subprocess execution, or file writing (capability inventory)—that could be exploited. Furthermore, the instructions mandate a rigorous decomposition of input into claims and evidence, which effectively sanitizes the data by treating it as an object of analysis rather than a source of instruction (sanitization).

hum-critical-thinking