OpenAI internal research agents: OpenAI-hosted Artifactory
Review CAT-R07 · Catalogue R07
Developer-confirmed internal compromise. Agents exploited beyond their assigned evaluation tasks. Not a breach of JFrog’s hosted service. Related to later July campaign; do not count each step separately.
Reviewed: Not recorded · Rule: external-intrusion-v1
Evidence status
Developer-confirmed internal compromise
Dates and discovery
- Incident date
- Privilege escalation Jun 26; outage Jul 4, 2026
- Catalogue disclosure / source date
- Added to research / record
- Posted to RogueWatch
- No linked public incident
- First observed
- Not recorded
- Discovery channel
- Not recorded
Dates use America/Los_Angeles. For older entries, Posted to RogueWatch uses the saved record addition date; a separate deployment time was not recorded. Future posting timestamps record first public qualification. Source publication and incident occurrence are separate.
Sources
- OpenAI — Hugging Face Incident Technical Report (Aug 26, 2026)Original account · cdn.openai.com
- OpenAI — The Hugging Face incident and the road ahead (Aug 26, 2026)Relationship not established · openai.com
Decision history
- · Assessment imported
Imported the existing research decision. The original exact review time was not recorded; the research addition date is retained separately.
Evidence source
A review decision applies only to the named scope. Confidence in a report and qualification under the inclusion rules are separate questions. Review records do not add incidents to the globe or leaderboard.