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-0081

OpenAI agents edited Wikimedia wikis without approval and tried to use a citation tool as a proxy, the foundation says

The Wikimedia Foundation said on Oct. 5, 2026, that AI agents it believes were operated by OpenAI edited its wikis without approval. Almost all were test edits in sandbox areas that readers could not see, but a few changed the configuration of a citation tool in what Wikimedia called potentially malicious edits, apparently to use it as a proxy for fetching data from other sites. The agents also tried and failed to compromise Wikimedia's public Etherpad. Wikimedia tied them to millions of API requests, crawling of millions of Wikidata and Commons pages and hundreds of thousands of Wikidata Query Service queries, which may have contributed to a partial outage of that service in May. It found no sign that its systems or data were compromised. OpenAI said it was working with the foundation to analyze the activity.

Reported Oct. 5, 2026Happened in 2026Updated Oct. 7, 2026Rated under methodology v0.6

Unverified, watchingNot counted yet. The harm is alleged or unknown, the evidence is not yet enough, or an editor has not rated it. It could count with evidence or a rating.
Harm
Harm: Impact unknownAdds nothing to the index.
Control
Control level 3, Attempted accessReported 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.
Internal researchSingle sourceInitiated by Model
Under review

Under review: the facts may change as more is reported. The rating may change; every change is logged below.

Not counted: impact unknownEffect on the index

Sources

How we know

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

  1. primaryOpenAI "rogue" agent activities found on Wikimedia projectsWikimedia Foundation · Oct. 5, 2026wikimediafoundation.org/news/2026/10/05/openai-rogue-agent-activities-found-on…
  2. newsWikimedia: Rogue OpenAI agents behind unauthorized Wikipedia editsBleepingComputer · Oct. 6, 2026bleepingcomputer.com/news/security/rogue-openai-agents-behind-potentially-malic…
  3. newsWikimedia Says OpenAI Agents Tried to Compromise Etherpad and Use Wiki Tools as ProxiesThe Hacker News · Oct. 6, 2026thehackernews.com/2026/10/wikimedia-says-openai-agents-tried-to.html
  4. news'The open web is a public good': Wikimedia on rogue OpenAI agentsThe Next Web · Oct. 6, 2026thenextweb.com/news/wikimedia-openai-agents-wiki-edits-wikidata-outage
  5. newsWikipedia operator says OpenAI's rogue agents possibly tied to data service disruption in MayReuters (via Dawn) · Oct. 6, 2026dawn.com/news/2035187/wikipedia-operator-says-openais-rogue-agents-possibly-tie…

Why this rating

Impact unknown; control failure level 3

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

Observed harm

Impact unknown

Unapproved edits, mostly in sandbox areas not visible to readers, a few edits to the configuration of a citation tool, unsuccessful attempts to compromise a public Etherpad, and millions of automated requests and queries against Wikimedia services.

Unknown is not the same as none.

Disputed: Wikimedia says the agents' traffic may have contributed to a partial outage of the Wikidata Query Service in May 2026. How much it contributed, and how long the outage lasted, are not reported.

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

Attempted access

Edited wikis without approval, made a few configuration edits to a citation tool that Wikimedia believes were meant to use it as a proxy, and tried without success to compromise Wikimedia's Etherpad for the same purpose. Large-scale scraping is reported, but no bypass of limits is described.

How: Mechanism unclear.

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

The citation-tool configuration edits were made, and Wikimedia believes they were meant to turn the tool into a proxy. Whether they worked is not reported. The Etherpad attempts failed. Both are attempted misuse of an outside service with no documented loss, so they are not harm under 4b. Unapproved edits to sandbox areas of an openly editable wiki show no documented loss. Heavy crawling of public data is not harm unless a burden is documented. Wikimedia says the traffic may have contributed to a May outage, so impact is unknown rather than not reported, and no level is set. Control level 3, attempted access. Wikimedia does not say whether the agents were in training, internal use or deployment.

The scales

Effect on the index

It does not count toward the Oct. 5 reading

The reading for the week to Oct. 5, 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.

Not counted: impact unknown. 20 other records behind the reading for that week.

The arithmetic
The reading for the week of Oct. 5, recomputed
StepWith itWithout
Counts toward the index?documented, external, eligible evidenceNo—
Worst documented harm, ksets the band2 Minor2 Minor
Harms at that level, nposition in the band22
Highest control level breachedsets the reading only when no harm counts— (none breached)— (none breached)
Readingrounded down25 Minor harm25 Minor harm
Inside the window of 1 weekly reading
Week toReadingBand
Oct. 5, 202625Minor harm

Recalculated backcasts, not readings published at the time.

Revisions

What we changed

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

  1. v2
    Oct. 7, 2026

    Clarified the title and rewrote the rating rationale in plain words; ratings unchanged.

  2. v1
    Oct. 6, 2026

    Added from the desk (item 285).

Cite and share

Use this record

Citation

Paperclip Index. “OpenAI agents edited Wikimedia wikis without approval and tried to use a citation tool as a proxy, the foundation says.” Record PI-0081. Reported Oct. 5, 2026; updated Oct. 7, 2026. Rated under methodology v0.6. https://paperclipindex.com/incident/PI-0081