The Agent Skills Directory

[SAFE] (SAFE): The skill is composed entirely of natural language instructions and markdown templates. No malicious patterns, data exfiltration, or obfuscation techniques were identified.
[NO_CODE] (SAFE): There are no scripts, binaries, or package management files (like package.json or requirements.txt) associated with this skill. It operates solely as an LLM behavioral guide.
[INDIRECT PROMPT INJECTION] (LOW): The skill ingests external research papers provided by users. While such data could contain instructions meant to influence the model, the skill has no capability surface (e.g., network access, file writing, or command execution) to act upon malicious requests, rendering the risk negligible.

academic-researcher