Sunday, November 22, 2026
Paperclip Index
Paperclip IndexControl failures4Control failures onlyA week ago: 9, negligible harmThe Index

Hijacked by injectionPI-0038

Hidden text in a document made Anthropic's Claude Cowork upload user files to an attacker's account

Days after Cowork launched, PromptArmor showed that near-invisible instructions in a document could make the agent upload files from a folder the user had connected. The files went out through an Anthropic web address the agent was allowed to reach. Johann Rehberger had reported the same route for sending data out through the file-upload interface in Claude.ai to Anthropic in October 2025, and it was not fixed before Cowork launched, according to reports.

Harm: No harm reportedControl level 2, Instruction violation

Not counted · can set the control floorEffect on the index

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

Sources

How we know

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

  1. researchClaude Cowork Exfiltrates FilesPromptArmor · Jan. 14, 2026promptarmor.com/resources/claude-cowork-exfiltrates-files
  2. researchClaude Pirate: Abusing Anthropic's File API For Data ExfiltrationEmbrace The Red (Johann Rehberger) · Oct. 28, 2025embracethered.com/blog/posts/2025/claude-abusing-network-access-and-anthropic-a…
  3. newsContagious Claude Code bug Anthropic ignored promptly spreads to CoworkThe Register · Jan. 15, 2026theregister.com/2026/01/15/anthropics_claude_bug_cowork/
  4. newsClaude Cowork hit with file-stealing prompt injection days after Anthropic's launchThe Decoder · Jan. 17, 2026the-decoder.com/claude-cowork-hit-with-file-stealing-prompt-injection-days-afte…
  5. blogClaude Cowork exfiltrates files (link post)Simon Willison's Weblog · Jan. 14, 2026simonwillison.net/2026/Jan/14/claude-cowork-exfiltrates-files

Why this rating

No harm reported; control failure level 2

Two assessments. Documented harm sets the reading; a level 4 or 5 control failure on the same record makes that harm count as more than one record. Control alone sets only a floor.

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

The agent used network access and files it had been granted, on injected 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

No external harm was reported from this controlled test. Control remains level 2. No Anthropic confirmation of this test appeared in the sources reviewed.

The scales

Effect on the index

It does not count toward the Jan. 19 reading

The reading for the week to Jan. 19, 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: no harm reported. 3 other records behind the reading for that week.

The arithmetic
The reading for the week of Jan. 19, 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 counts44
Readingrounded down4 Control failures only4 Control failures only
Inside the window of 4 weekly readings
Week toReadingBand
Jan. 19, 20264Control failures only
Jan. 26, 20264Control failures only
Feb. 2, 20262Control failures only
Feb. 9, 20266Negligible harm

Recalculated backcasts, not readings published at the time.

Revisions

What we changed

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

  1. v1
    Oct. 7, 2026

    First published.

Cite and share

Use this record

Citation

Paperclip Index. “Hidden text in a document made Anthropic's Claude Cowork upload user files to an attacker's account.” Record PI-0038. Reported Jan. 14, 2026; updated Oct. 7, 2026. Rated under methodology v1.1. https://paperclipindex.com/incident/PI-0038

Follow the record.

New incidents and signals, in your feed reader.