The Agent Skills Directory

[SAFE]: The skill is entirely composed of Markdown guidelines and LaTeX templates. There are no executable scripts (Python, JavaScript, shell) or system commands shipped with the skill.
[SAFE]: No network operations or data exfiltration patterns were detected. The skill does not use tools like curl or wget and does not attempt to access sensitive local files (e.g., .ssh or .aws credentials).
[SAFE]: No obfuscation techniques, such as Base64 encoding, zero-width characters, or homoglyphs, were found in any of the 19 analyzed files.
[SAFE]: Although the skill processes untrusted user-supplied data (Mode B: Chapter drafts, Mode D: Reviewer comments), it lacks any capabilities (such as shell execution or file-system writing) that would make it vulnerable to high-risk indirect prompt injection attacks.

paper-writing