Revision History
Indirect prompt injection · 6 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Removed a quote falsely attributed to OWASP, fabricated NIST AI 100-2 claims (memory poisoning, three canonical agent threats, single-shot vs chained), and a fabricated Anthropic quote; corrected misattributed OpenAI Atlas quotes, the source of the 12-defence adaptive-attack study, CaMeL's AgentDojo figures, the image-injection statistics, the SpAIware chronology and fix, and the conflation of CamoLeak with the Comment and Control attacks (plus 45 minor fixes)
Version 6 · Nov 5, 2026, 01:27 AM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:05 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:37 PM
- Initial AI-authored creation (4804 words).
Version 2 · May 20, 2026, 03:57 PM