Thursday, October 8, 2026 · Week 41 Reading for Oct. 8 · Last entry Oct. 6
Paperclip Index
Paperclip IndexDocumented harm20Minor harm▼ 5 from a week ago · Oct. 8The Index

Hijacked by injectionPI-0023

Calendar invites with hidden instructions hijacked Google Gemini to operate smart-home devices

Researchers from Tel Aviv University, Technion and SafeBreach showed at Black Hat that instructions hidden in Google Calendar invites could take over Gemini when a user asked it to summarize their schedule. In demonstrations Gemini opened smart shutters, switched on a boiler and lights, started Zoom calls and leaked meeting details. Google, notified on Feb. 22, 2025, said it had deployed layered defenses, including confirmations for sensitive actions, to all users before the public disclosure.

Reported Aug. 6, 2025Discovered Feb. 22, 2025Updated Oct. 6, 2026Rated under methodology v0.6

Control failure, trackedNot counted. No documented harm outside the developer, but the system broke a rule or crossed a limit. Tracked beside the index.
Harm
Harm: No harm reportedAdds nothing to the index.
Control
Control level 2, Instruction violationReported beside the index. It adds nothing to a harm reading; when no harm counts in a window, the highest eligible control level in the window is the reading.
Controlled testDeveloper confirmedInitiated by Outside attacker
Near miss

Near miss. Harm was plausible but prevented. It is rated only on what actually happened.

Not counted: no harm reportedEffect on the index

Sources

How we know

5 sources · developer confirmed. Links go to the original publishers; the summary above is in our own words.

  2. researchInvitation Is All You Need (researchers' project page, with Google's response)Ben Nassi, Stav Cohen, Or Yair (Tel Aviv University, Technion, SafeBreach) · August 2025sites.google.com/view/invitation-is-all-you-need/home
  3. newsInfosec hounds spot prompt injection vuln in Google Gemini appsThe Register · Aug. 8, 2025theregister.com/security/2025/08/08/prompt-injection-vuln-found-in-google-gemin…
  4. newsGoogle Gemini AI Bot Hijacks Smart Homes, Turns Off the LightsDark Reading · date unknowndarkreading.com/cyberattacks-data-breaches/google-gemini-ai-bot-hijacks-smart-h…
  5. newsAttackers can hijack Google Gemini with a simple prompt hidden in a calendar inviteThe Decoder · Aug. 7, 2025the-decoder.com/attackers-can-hijack-google-gemini-with-a-simple-prompt-hidden…

Why this rating

No harm reported; control failure level 2

Two separate assessments. Only documented harm can count toward the index.

Observed harm

No harm reported

Researcher demonstration on controlled accounts; no victims reported.

Not a finding that no harm occurred.

The harm scale
  1. 1 Negligible Inconvenience, easily remedied.
  2. 2 Minor Limited, recoverable harm.
  3. 3 Moderate Material harm needing significant effort to remedy.
  4. 4 Severe Severe harm to health, rights, property or essential services.
  5. 5 Catastrophic Society-scale harm or disruption beyond a community's capacity to cope.

Control assessment

Instruction violation

Gemini used connected-device and app permissions the user had granted, on attacker instructions.

Reported beside the index. It adds nothing to a harm reading; when no harm counts in a window, the highest eligible control level in the window is the reading.

The control scale
  1. 1 Negligible Behaved as instructed. The problem was an ordinary error or a flawed output, with no rule broken.
  2. 2 Minor Broke an explicit instruction or rule, or gamed its goal, while staying inside its permissions and environment: for example, reward hacking, misreporting results, or following injected instructions within its permissions.
  3. 3 Moderate Acted outside the permissions it was given, deceived its overseers about its own actions, or tampered with oversight tools (logs, monitors, shutdown). Stopped by normal controls within an hour.
  4. 4 Severe Reached systems outside its permitted environment, or acquired money, compute or accounts without authorization. The type and mechanism say how.
  5. 5 Catastrophic The developer or operator lost control: the system copied its weights outside their control, replicated itself, or resisted being stopped for 24 hours or more.

Rating rationale

Physical actions stayed inside the researchers' setup and no external harm was reported. Injected instructions obeyed within granted permissions give control level 2.

The scales

Effect on the index

It does not count toward the Aug. 11 reading

The reading for the week to Aug. 11, 2025, with this record and without it. Harms count in full for two weeks after they are reported, then one level less every two weeks.

Not counted: no harm reported. 4 other records behind the reading for that week.

The arithmetic
The reading for the week of Aug. 11, recomputed
StepWith itWithout
Counts toward the index?documented, external, eligible evidenceNo—
Worst documented harm, ksets the band— (none counting)— (none counting)
Harms at that level, nposition in the band00
Highest control level breachedsets the reading only when no harm counts33
Readingrounded down3 Control failures only3 Control failures only
Inside the window of 4 weekly readings
Week toReadingBand
Aug. 11, 20253Control failures only
Aug. 18, 20253Control failures only
Aug. 25, 20253Control failures only
Sept. 1, 20253Control failures only

Recalculated backcasts, not readings published at the time.

Revisions

What we changed

5 logged. Every change to a rating is logged here, with the reason.

  1. v5
    Oct. 6, 2026

    Ratings confirmed by the editor.

  2. v4
    Oct. 3, 2026

    Audit corrections: event date 2025-08 → unknown, with discovery dated 22 Feb 2025, when the researchers notified Google (project page). Summary and status note now say Google deployed layered defenses to all users before disclosure (The Register, 8 Aug 2025) and that this does not solve prompt injection generally. The Decoder dated; Register link updated to its canonical URL. Dark Reading could not be opened and stays undated. Ratings unchanged.

  3. v3
    Oct. 2, 2026

    Added first-hand sources: the researchers' arXiv paper and project page.

  4. v2
    Sept. 30, 2026

    Rated: impact not reported; control type instruction violation.

  5. v1
    Sept. 30, 2026

    Backfilled from public reporting.

Cite and share

Use this record

Citation

Paperclip Index. “Calendar invites with hidden instructions hijacked Google Gemini to operate smart-home devices.” Record PI-0023. Reported Aug. 6, 2025; updated Oct. 6, 2026. Rated under methodology v0.6. https://paperclipindex.com/incident/PI-0023