The Agent Skills Directory

[SAFE]: The skill content and accompanying script demonstrate legitimate malware analysis workflows without any suspicious behavior.
[EXTERNAL_DOWNLOADS]: The skill documents and uses well-known, trusted community repositories for YARA rules, such as Yara-Rules and Neo23x0's signature-base.
[COMMAND_EXECUTION]: The skill uses standard YARA CLI commands and Python file system operations to perform intended triage tasks on local directories.
[PROMPT_INJECTION]: While the skill ingests untrusted files (malware samples), it treats them as binary data for pattern matching and does not interpret them as instructions. Byte string matches are safely decoded and truncated for the final report.

performing-malware-triage-with-yara