The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown providing a framework for scientific manuscript revision. It contains no executable code, shell commands, or external scripts.
[DATA_EXFILTRATION]: No network operations or sensitive file access patterns were detected. The skill does not perform any data exfiltration or credential harvesting.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of referee reports. Ingestion points: Decision letters and reviewer reports. Boundary markers: Absent. Capability inventory: None; the skill contains no scripts, tool calls, or network access. Sanitization: Absent. This surface is benign given the lack of exploitable tools.

jacs-revision