I take it you're not interested in later words like sultanus, algebra, alcohol or nadir. Then I hope that this article from 1892 isn't too outdated: 'On Semitic Words in Greek and Latin' by W. Muss-Arnolt (https://www.jstor.org/stable/2935792?seq=1#metadata_info_tab_contents). If you search for "lat." within the pdf, or look in the index at the end, you'll find a few candidates.
However, it is sometimes difficult to determine whether a word was loaned into Latin through Greek, or independently. When the Latin is deformed exactly the same way as the Greek, or contains typically Greek letters or letter combinations like 'y', 'rrh', or 'ch/th/ph', it probably came through Greek. But what about e.g. galbanum and χαλβάνη from Hebr. חלבה, or cummis/gummis and κόμμι from Egyptian kemai? Maybe these did come through Greek, but were adapted to pre-existing Latin words through folk-etymology, or changed for some other or no reason.
I found these ones which the author derives directly from Semitic languages (or cites without disagreement others who do so):
- pinna: from Semitic פנה - but L&S refer the reader to penna which is IE, and pīna from Greek
- macellum, macellotae: from Semitic מכלא, pl. mākhəlōth - but Wiktionary derives the first from macula, and L&S compares it to μάχαιρα and mactare
- mappa: see Hebrew מפר - Wiktionary says that Quintilian called it Punic, L&S cite him: "mappam usitatum Circo nomen, Poeni sibi vindicant"
- jubilare: from Hebrew יובל - but Wiktionary and De Vaan say it's from a Proto-Italic stem *jū- (with the same suffix as si-bilare)
- idus: from Semitic `īd (see Ar. عيد) - but Wiktionary says the Arabic comes from the Latin. De Vaan agrees with Varro that it's Etruscan.
He says he doesn't think omasum comes from חמש, but doesn't say why. According to L&S it's Gallic, according to Wiktionary 'probably' Celtic/Gaulish, but "compare Hebrew חֹ֫מֶשׁ".