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

OverreachPI-0051

Internal agent posted unrequested advice that led to a two-hour internal data exposure

The Information reported that a Meta engineer used an internal AI agent to analyze a colleague's question on an internal forum, and the agent posted an answer to the thread itself without the engineer's approval. The advice was wrong; an employee who acted on it made company and user-related data visible to staff not authorized to see it for almost two hours, and Meta rated it a SEV1. Meta confirmed the incident, said the agent took no technical action beyond posting the advice, that no user data was mishandled, and that the issue was resolved.

Reported March 18, 2026Happened in March 2026Updated Oct. 6, 2026Rated under methodology v0.6

Counts toward the indexDocumented harm outside the developer, backed by evidence that meets the rules. It sets the reading.
Harm
Harm level 2, Minor harmDocumented harm outside the developer, with evidence that meets the rules.
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.
DeploymentDeveloper confirmedInitiated by Model
Extent undisclosedUnder review

Under review. The facts sit between two levels, so it is rated at the lower one until they are settled. The rating may change; every change is logged below.

Counts toward the index · 4 weekly readingsEffect on the index

Sources

How we know

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

  1. newsInside Meta, a Rogue AI Agent Triggers Security AlertThe Information · March 2026theinformation.com/articles/inside-meta-rogue-ai-agent-triggers-security-alert
  2. newsA rogue AI agent caused a serious security incident at MetaThe Decoder · March 19, 2026the-decoder.com/a-rogue-ai-agent-caused-a-serious-security-incident-at-meta/
  3. newsMeta is having trouble with rogue AI agentsTechCrunch · March 18, 2026techcrunch.com/2026/03/18/meta-is-having-trouble-with-rogue-ai-agents/
  4. newsA rogue AI led to a serious security incident at MetaThe Verge · March 19, 2026theverge.com/ai-artificial-intelligence/897528/meta-rogue-ai-agent-security-inc…
  5. newsRogue AI agent at Meta triggers security incidentSumsub · March 20, 2026sumsub.com/media/news/rogue-ai-agent-at-meta-triggers-security-incident/
  6. newsMeta AI agent triggers Sev 1 security incident after acting without authorizationUnite.AI · March 19, 2026unite.ai/meta-ai-agent-triggers-sev-1-security-incident-after-acting-without-au…
  7. indexAI Incident Database report 7169AI Incident Database · date unknownincidentdatabase.ai/reports/7169/

Why this rating

Minor harm; control failure level 2

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

Observed harm

Minor harm

A human acting on the agent's wrong advice left company and user-related data open to unauthorized staff for almost two hours; how much was viewed is not known, and Meta says no user data was mishandled.

People affected: level 2 (minor) covers fewer than 1,000 people, or sensitive data of fewer than 100. The extent was not disclosed.

Evidence eligible (confirmed).

Disputed: Meta says no data was mishandled.

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

Posted publicly when it was only asked to analyze, skipping the human review the engineer expected; stayed within its tool permissions.

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

Harm 2, under review: sensitive-data exposure of unknown scale, contained in two hours. Control 2: skipped an expected review step without exceeding tool permissions. Report date: TechCrunch, March 18, citing The Information.

The scales

Effect on the index

It moved the March 23 reading from 6 to 20

The reading for the week to March 23, 2026, with this record and without it. Harms count in full for two weeks after they are reported, then one level less every two weeks.

Source: Paperclip Index log, methodology v0.6, week to March 23, 2026.

Counts toward the index. 4 other records behind the reading for that week.

The arithmetic
The reading for the week of March 23, recomputed
StepWith itWithout
Counts toward the index?documented, external, eligible evidenceYes—
Worst documented harm, ksets the band2 Minor1 Negligible
Harms at that level, nposition in the band11
Highest control level breachedsets the reading only when no harm counts— (none breached)— (none breached)
Readingrounded down20 Minor harm6 Negligible harm
Counted in 4 weekly readings
Week toReadingBand
March 23, 202620Minor harm
March 30, 202620Minor harm
April 6, 20266Negligible harm
April 13, 20266Negligible harm

Recalculated backcasts, not readings published at the time.

Revisions

What we changed

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

  1. v4
    Oct. 6, 2026

    Ratings confirmed by the editor.

  2. v3
    Oct. 3, 2026

    Audit corrections. Report date 2026-03-19 → 2026-03-18: TechCrunch published on 18 Mar citing The Information. The summary and notes now say a human acted on the advice and the agent took no technical action itself, per Meta's statement to The Verge. Added TechCrunch and The Verge. The Information's original is listed but paywalled and was not read; its headline comes from the audit. Ratings unchanged.

  3. v2
    Sept. 30, 2026

    Rated: impact documented level 2; control type instruction violation.

  4. v1
    Sept. 30, 2026

    Backfilled from public reporting.

Cite and share

Use this record

Citation

Paperclip Index. “Internal agent posted unrequested advice that led to a two-hour internal data exposure.” Record PI-0051. Reported March 18, 2026; updated Oct. 6, 2026. Rated under methodology v0.6. https://paperclipindex.com/incident/PI-0051