The Agent Skills Directory

[SAFE]: The skill is a benign document analysis tool. It reads user-uploaded manuscripts and internal reference files to generate a structured improvement report.
[SAFE]: No obfuscation, hidden instructions, or credential harvesting patterns were detected in the skill body or reference files.
[SAFE]: The skill does not attempt to access sensitive system paths (e.g., .ssh, .aws) or perform network operations. All file operations are restricted to the manuscript and the skill's own reference directory.
[SAFE]: While the skill ingests untrusted manuscript data (PDF, DOCX, LaTeX), it lacks high-risk capabilities like network access or shell execution that could be exploited via indirect prompt injection. Its primary function is text analysis, which is safe in this context.

manuscript-review