The Agent Skills Directory

[SAFE]: The skill contains instructional text, formatting rules, and process facts intended to guide an AI agent in checking a user's manuscript. It does not include executable scripts, network commands, or any mechanism for data exfiltration.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data (manuscripts provided by the user). While it does not implement explicit boundary markers or sanitization, it lacks any high-privilege capabilities (such as shell execution, file writing, or network access) that could be exploited by malicious content within a manuscript.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill references legitimate, well-known academic services such as Manuscript Central and the Open Science Framework (OSF). These are documented for reference purposes only and do not involve credential harvesting or exfiltration of sensitive system data.

psci-submission