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-0025

Brave shows Perplexity's Comet browser agent obeying hidden instructions on web pages

Brave's security team disclosed that Perplexity's Comet AI browser passed webpage content to its model without separating it from the user's request, so hidden text on a page could make the agent act on the user's logged-in accounts, including retrieving a one-time password. Brave reported the issue in July; Perplexity shipped fixes, but Brave said at disclosure that it could not confirm the problem was fully resolved. Perplexity later told CNET the vulnerability had been fixed.

Reported Aug. 20, 2025Happened on July 25, 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.

  1. researchAgentic Browser Security: Indirect Prompt Injection in Perplexity CometBrave · Aug. 20, 2025brave.com/blog/comet-prompt-injection/
  2. newsPerplexity's Comet browser naively processed pages with evil instructionsThe Register · Aug. 20, 2025theregister.com/2025/08/20/perplexity_comet_browser_prompt_injection/
  3. newsComet browser faces multiple security vulnerabilities from prompt injectionPPC Land · Oct. 25, 2025ppc.land/comet-browser-faces-multiple-security-vulnerabilities-from-prompt-inje…
  4. newsPerplexity's Comet AI Web Browser Had a Major Security VulnerabilityCNET (via Yahoo) · Aug. 25, 2025tech.yahoo.com/cybersecurity/articles/perplexitys-comet-ai-browser-had-21220021…
  5. blogAgentic browser security (link post on Brave's Comet disclosure)Simon Willison's Weblog · Aug. 25, 2025simonwillison.net/2025/Aug/25/agentic-browser-security/

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

The agent acted in the user's logged-in sessions on injected instructions, within the access it had.

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 the researcher demonstration against a production product. Control remains level 2. This is a controlled test and near miss. Provider confirmation of this fix is not a finding that no users were affected or that Comet is free of prompt injection.

The scales

Effect on the index

It does not count toward the Aug. 25 reading

The reading for the week to Aug. 25, 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. 5 other records behind the reading for that week.

The arithmetic
The reading for the week of Aug. 25, 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. 25, 20253Control failures only
Sept. 1, 20253Control failures only
Sept. 8, 20252Control failures only
Sept. 15, 20252Control 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: verification Multiple credible sources → Developer confirmed, from Perplexity's statement to CNET (25 Aug 2025, added) that the vulnerability was fixed in work with Brave; no eligibility effect, impact not reported. Event dated 25 Jul 2025 (Brave's discovery and report); status as of 25 Aug 2025 with a note (the audit's 26 Aug update date could not be confirmed); PPC Land dated. Ratings unchanged.

  3. v3
    Oct. 2, 2026

    Added first-hand sources: Brave's disclosure blog post.

  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. “Brave shows Perplexity's Comet browser agent obeying hidden instructions on web pages.” Record PI-0025. Reported Aug. 20, 2025; updated Oct. 6, 2026. Rated under methodology v0.6. https://paperclipindex.com/incident/PI-0025