The Agent Skills Directory

[SAFE]: The skill is entirely composed of natural language instructions related to library science and preservation techniques.
[PROMPT_INJECTION]: No override markers or jailbreak patterns were identified in the instructional text.
[DATA_EXFILTRATION]: The skill does not access sensitive file paths or perform unauthorized network operations.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or unverified packages.
[COMMAND_EXECUTION]: No shell commands, system modifications, or privilege escalation attempts were found.
[OBFUSCATION]: The content is clear and does not utilize encoding, zero-width characters, or hidden text to mask malicious intent.

preserve-materials