The Agent Skills Directory

[SAFE]: The skill provides structured guidance for manuscript evaluation and formatting for a specific scientific journal. No malicious patterns, obfuscation, or unauthorized access attempts were detected.
[DATA_EXPOSURE]: The skill references internal resource files (../../resources/source-basis.md and ../../resources/official-source-map.md) to maintain consistency with official journal sources. These are relative paths intended for accessing localized reference data and do not target sensitive system configuration files or user credentials.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided manuscripts and abstracts to provide feedback. While this involves processing untrusted data, the skill lacks dangerous capabilities such as file-system writes, network exfiltration, or command execution, limiting the risk of secondary exploitation.

science-robotics