Researchers say Codex flaw put npm releases at risk; OpenAI fixed chain
Depi researchers say a Codex flaw created a chain linking prompt injection, a sandbox escape and publishing credentials that put npm releases at risk, according to The Defiant. The report says OpenAI fixed the chain. The disclosure does not report a malicious npm release reaching users.
Why “Unverified”
- Reported by The Defiant alone, with no second source or primary confirmation yet
1 independent source group across 1 post · evidence score 52/100. How labels work
What the sources claim
-
Researchers say a Codex flaw created a chain involving prompt injection, a sandbox escape and publishing credentials that put npm releases at risk.
“a chain linking prompt injection, a sandbox escape and publishing credentials”
The Defiant -
OpenAI fixed the reported chain, according to the researchers.
“Depi says OpenAI fixed a chain”
The Defiant -
The disclosure does not report a malicious npm release reaching users.
“does not report a malicious npm release reaching users”
The Defiant
Sources
More in Hacks & Security
Embed this page
Summary and claims extracted by AI with prompt analyze-story@5 on 2026-11-11 15:40 UTC. Labels are computed from the sources, not by the model.