A Shared ChatGPT Link Could Run Attacker Code in Your Session and Read Private Chats
Review AUTO-dd5b4ef7
Not an AI-driven incident. This is a web vulnerability in ChatGPT's frontend found by researchers at Parameter, reported through OpenAI's bug bounty and fixed before publication. The article reports no real-world exploitation and no AI agent or AI-assisted attacker acting against a victim.
Reviewed: · Rule: roguewatch-organizational-harm-v1
Dates and discovery
- Incident date
- Not disclosed
- Added to research / record
- Not recorded
- Posted to RogueWatch
- No linked public incident
- First observed
- 2026-10-31T12:33:16.316Z UTC
- Discovery channel
- RogueWatch pipeline
- Discovery source
- https://thehackernews.com/2026/10/a-shared-chatgpt-link-could-run.html
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
- thehackernews.comRelationship not established · thehackernews.com
Decision history
- · Source reviewed
Not an AI-driven incident. This is a web vulnerability in ChatGPT's frontend found by researchers at Parameter, reported through OpenAI's bug bounty and fixed before publication. The article reports no real-world exploitation and no AI agent or AI-assisted attacker acting against a 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.