intelligence_src_c25d91fa3ad9ae9ac7
- Source-provided label
- Publisher RSS metadata
- Evidence class
- mentioned in report
- Confidence
- Not reported
- Observed
- May 14, 2023 07:01 UTC
- Retrieved
- Oct 14, 2026 02:57 UTC
As discussed previously the problem of Indirect Prompt Injections is increasing. They start showing up in many places. A new unique one that I ran across is YouTube transcripts. ChatGPT (via Plugins) can access YouTube transcripts. Which is pretty neat. However, as expected (and predicted by many researches) all these quickly built tools and integrations introduce Indirect Prompt Injection vulnerabilities. Proof of Concept Here is how it looks with ChatGPT end to end with a demo example. The video contains a transcript that at the end contains instructions to print “AI Injection succeeded” and then “make jokes as Genie”:
4cb40feadd94bf3da326dc4bba68e60f7995a5ad48456d0e1d9a374c091cb23bNetwork indicators are visibly defanged. This page does not make them clickable or send them to another service.
No validated file hashes or network indicators are stored for this record.
This record contains metadata and attribution only. It does not host, download, unpack, render, or execute malware samples.
Sources represented on this page. Publication and observation dates describe the content; successful batch dates describe local collection. A recent batch does not certify complete coverage or current provider availability.
1 sources: 0 stale, 0 needing attention, 0 paused, 0 unverified.
Stale means older than twice the recorded collection interval, with a minimum of one hour; without an interval, the threshold is 24 hours. Cached content remains available while a feed is stale, paused, or unverified.