The Agent Skills Directory

[SAFE]: The skill is a collection of Markdown files (SKILL.md, reference catalogs, and templates) providing instructions for a scientific reasoning protocol. No malicious activities, obfuscation, or unauthorized access patterns were detected.- [NO_CODE]: The skill package does not include any scripts (.sh, .py, .js), binaries, or configuration files that execute logic on the host system. It relies purely on the agent's internal reasoning capabilities.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied questions through its 5-stage protocol. While the agent ingests untrusted data from users, the skill does not grant or use high-risk capabilities like non-standard file writes or network exfiltration, effectively mitigating the threat of indirect injection attacks.

falsify