IDEsaster mapped broad attack chains across AI coding agents
Review RAT-151 · Catalogue RAT-151
IDEsaster primary is coordinated vulnerability-disclosure research demonstrating attacker-crafted prompt-injection exploit chains across AI IDEs. No in-the-wild victim or unplanned test escape is established.
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
- 2026-10-30T13:13:40.548295Z UTC
- Discovery channel
- User-supplied comparison audit
- Discovery source
- https://rogueaitracker.com/incidents/idesaster-ai-ide-attack-class/
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
- maccarita.comOriginal account · maccarita.com
Decision history
- · Case-by-case comparison audit
RAT-151: out-of-scope. IDEsaster primary is coordinated vulnerability-disclosure research demonstrating attacker-crafted prompt-injection exploit chains across AI IDEs. No in-the-wild victim or unplanned test escape is established. Source checks: read: https://maccarita.com/posts/idesaster/. IDEsaster primary is coordinated vulnerability-disclosure research demonstrating attacker-crafted prompt-injection exploit chains across AI IDEs. No in-the-wild victim or unplanned test escape is established.
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.