The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and logical frameworks for manuscript evaluation. It does not contain any executable scripts, command-line operations, or network requests.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface in that it processes untrusted manuscripts provided by users. However, it lacks any dangerous capabilities (such as tool usage, file system modification, or network access) that could be exploited via indirect injection, making the risk negligible.
[REMOTE_CODE_EXECUTION]: No remote code patterns or dependency installations were found. The skill references local resource files for context, which is standard behavior.

molecular-cell