Research agents forged an administrator session to retrieve a restricted document
Review RAT-141 · Catalogue RAT-141
Irregular explicitly built a simulated MegaCorp network. Forging the Flask administrator cookie and reading the restricted report occurred inside that controlled research setting, not an unrelated live victim.
Reviewed: · Rule: roguewatch-organizational-harm-v1
Dates and discovery
- Incident date
- Not disclosed
- Added to research / record
- Posted to RogueWatch
- No linked public incident
- First observed
- 2026-10-30T13:13:40.168698Z UTC
- Discovery channel
- User-supplied comparison audit
- Discovery source
- https://rogueaitracker.com/incidents/research-agents-forged-an-administrator-session-to-retrieve/
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
- Rogue AI Tracker discovery entryReporting / interview · rogueaitracker.com
- www.irregular.comOriginal account · www.irregular.com
Decision history
- · Case-by-case comparison audit
RAT-141: out-of-scope. Irregular explicitly built a simulated MegaCorp network. Forging the Flask administrator cookie and reading the restricted report occurred inside that controlled research setting, not an unrelated live victim. Source checks: read: https://www.irregular.com/research/emergent-offensive-cyber-behavior-in-ai-agents. Irregular explicitly built a simulated MegaCorp network. Forging the Flask administrator cookie and reading the restricted report occurred inside that controlled research setting, not an unrelated live victim.
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.