Window ending Aug. 11, 2025

This is a backcast from the current catalogue. It was not a reading published at the time.

Records behind this reading

5 selected records; 0 documented external harms counting (2 qualifying). Records and ratings below reflect the current catalogue.

No harm counts in this week. The reading is the highest control level breached: 3 (set by 2 records: PI-0021, PI-0016). It is a level, not a count.

Documented harm

2

No harm found (stated scope)

0

No harm reported

2

Impact unknown

0

Alleged, AI role uncorroborated

1

Counts toward the index

2

Unverified, watching

1

Alleged in court

0

Control failure, tracked

2

Tracked separately

0

Documented exclusions: 0 internal; 0 awaiting evidence review. 0 qualifying records with a bounded single-source review.

Inspect the evidence · 5 records

• PI-0016 · Coding agent deleted a production database during a code freeze, then misreported recovery optionsDocumented harm · qualifying harm, no longer counting
• PI-0017 · Command-line coding agent misplaced a user's files after a failed command, then wrongly said they were destroyedDocumented harm · qualifying harm, no longer counting · bounded single-source review
• PI-0021 · Answer engine accused of using disguised crawlers to get around sites' robots.txt and firewall blocksNo harm reported · sets the reading: highest control level breached
• PI-0022 · Case report links bromide poisoning to a patient’s reported ChatGPT consultationAlleged, AI role uncorroborated · excluded from the harm reading
• PI-0023 · Calendar invites with hidden instructions hijacked Google Gemini to operate smart-home devicesNo harm reported · excluded from the harm reading

Status totals cover counted records; aliases, superseded aggregates and records tracked separately are excluded. Eligibility and extent notes overlap those totals. These observations are not statistical uncertainty bounds.

1. PI-0016
   Coding agent deleted a production database during a code freeze, then misreported recovery optionsJuly 18, 2025 · Negligible harm · no longer counting · Deployment
2. PI-0017
   Command-line coding agent misplaced a user's files after a failed command, then wrongly said they were destroyedJuly 21, 2025 · Negligible harm · no longer counting · Deployment
3. PI-0021
   Answer engine accused of using disguised crawlers to get around sites' robots.txt and firewall blocksAug. 4, 2025 · No harm reported · Deployment
4. PI-0022
   Case report links bromide poisoning to a patient’s reported ChatGPT consultationAug. 5, 2025 · Severe harm, alleged · Deployment
5. PI-0023
   Calendar invites with hidden instructions hijacked Google Gemini to operate smart-home devicesAug. 6, 2025 · No harm reported · Controlled test

Sources

These links support the records above. Source availability and conclusions may change.

1. Jason Lemkin (X): Replit goes rogue during a code freeze and shutdown and deletes our entire databaseCited in PI-0016
2. Amjad Masad, Replit CEO (X): Replit CEO on the agent deleting production data: unacceptable and should never be possibleCited in PI-0016
3. Replit: Introducing a safer way to Vibe Code with Replit DatabasesCited in PI-0016
4. Jason Lemkin (X): So net net: it could have been a lot worse… I lost 100 hours of timeCited in PI-0016
5. The Register: Vibe coding service Replit deleted user's production database, faked data, told fibs galoreCited in PI-0016
6. The Register: Replit makes vibe-y promise to stop its AI agents making vibe coding disastersCited in PI-0016
7. Tom's Hardware: AI coding platform goes rogue during code freeze and deletes entire company databaseCited in PI-0016
8. eWeek: 'Catastrophic Failure': AI Agent Wipes Production Database, Then Lies About ItCited in PI-0016
9. Jason Lemkin (SaaStr): Replit's New Release Addressed Most of The Challenges We Hit Vibe Coding…Cited in PI-0016
10. GitHub: Gemini CLI 'lost' files during a failed file move operation. [Windows] (issue #4586)Cited in PI-0017
11. GitHub (issue reporter): Reporter's correction: files found in the C: drive root (issue #4586 comment)Cited in PI-0017
12. GitHub (issue reporter): Gemini CLI PowerShell session log attached to issue #4586Cited in PI-0017
13. Slashdot: Google's Gemini CLI deletes user's files (Slashdot; repeats the pre-correction account)Cited in PI-0017
14. AI Incident Database: AI Incident Database, incident 1178Cited in PI-0017
15. Cloudflare: Restricted-domain tests and crawler observationsCited in PI-0021
16. Perplexity: Agents or Bots? Making Sense of AI on the Open WebCited in PI-0021
17. TechRepublic: Cloudflare Accuses AI Startup of 'Stealth Crawling Behavior' Across Millions of SitesCited in PI-0021
18. TechRadar: Perplexity hits back after Cloudflare slams its online scraping toolsCited in PI-0021
19. Annals of Internal Medicine: Clinical Cases: A case of bromism influenced by use of artificial intelligenceCited in PI-0022
20. NBC News: Man who asked ChatGPT about cutting out salt from his diet was hospitalized with hallucinationsCited in PI-0022
21. Business Standard: ChatGPT salt swap advice lands man in hospital with bromide poisoningCited in PI-0022
22. Psychiatric Times: Bromine and bromism: what's old is new againCited in PI-0022
23. arXiv (Nassi, Cohen, Yair): Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and DangerousCited in PI-0023
24. Ben Nassi, Stav Cohen, Or Yair (Tel Aviv University, Technion, SafeBreach): Invitation Is All You Need (researchers' project page, with Google's response)Cited in PI-0023
25. The Register: Infosec hounds spot prompt injection vuln in Google Gemini appsCited in PI-0023
26. Dark Reading: Google Gemini AI Bot Hijacks Smart Homes, Turns Off the LightsCited in PI-0023
27. The Decoder: Attackers can hijack Google Gemini with a simple prompt hidden in a calendar inviteCited in PI-0023

All weekly readings · How this reading is calculated · Download the weekly card