LLM-driven script generation: PromptLock
Review CAT-X06 · Catalogue X06
EXCLUDED — proof of concept. Predefined malware prompts; not demonstrated rogue origin. Do not describe as a confirmed autonomous corporate intrusion.
Reviewed: Not recorded · Rule: external-intrusion-v1
Academic proof of concept.
Reviewed: Not recorded · Rule: roguewatch-organizational-harm-v1
Evidence status
EXCLUDED — proof of concept
Dates and discovery
- Incident date
- Discovered by Aug 27, 2025
- 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
- ESET Research — ESET discovers PromptLock (Aug 27, 2025)Original account · www.eset.com
- cloud.google.comRelationship not established · cloud.google.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 - Not recorded · Retained review-queue assessment
Academic proof of concept.
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.