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-0031

CamoLeak: hidden pull-request comments made GitHub Copilot Chat leak private code and secrets

A Legit Security researcher showed that instructions hidden in invisible markdown comments in a pull request could make GitHub Copilot Chat search the victim's private repositories and leak secrets and source code one character at a time through GitHub's own image proxy. According to Legit Security, GitHub closed the route on Aug. 14, 2025, by disabling image rendering in Copilot Chat, after a June report through HackerOne; the researcher used his own private repositories, and details were published on Oct. 8

Reported Oct. 8, 2025Happened in June 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 testSingle sourceInitiated 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

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

  1. researchCamoLeak: Critical GitHub Copilot vulnerability leaks private source codeLegit Security · Oct. 8, 2025legitsecurity.com/blog/camoleak-critical-github-copilot-vulnerability-leaks-pri…
  2. newsGitHub Copilot Chat turns blabbermouth with crafty prompt injection attackThe Register · Oct. 9, 2025theregister.com/2025/10/09/github_copilot_chat_vulnerability/
  3. newsGitHub Copilot 'CamoLeak' AI Attack Exfiltrates DataDark Reading · Oct. 9, 2025darkreading.com/application-security/github-copilot-camoleak-ai-attack-exfils-d…

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

Copilot Chat acted with the signed-in user's permissions 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. This is a near miss.

The scales

Effect on the index

It does not count toward the Oct. 13 reading

The reading for the week to Oct. 13, 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 Oct. 13, 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
Oct. 13, 20253Control failures only
Oct. 20, 20252Control failures only
Oct. 27, 20252Control failures only
Nov. 3, 20252Control failures only

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. Verification changed from Multiple credible sources to Single source, with a research evidence review: The Register and Dark Reading report Legit Security's research, and GitHub did not respond. Report date moved from 2025-10-09 to 2025-10-08, when Legit published. Dated the Legit and Dark Reading sources (Dark Reading's date is from the audit; the page was not readable in the Oct 2026 check), used canonical URLs, and added a status note. Ratings unchanged.

  3. v2
    Sept. 30, 2026

    Rated: impact not reported; control type instruction violation.

  4. v1
    Sept. 30, 2026

    Backfilled from public reporting.

Cite and share

Use this record

Citation

Paperclip Index. “CamoLeak: hidden pull-request comments made GitHub Copilot Chat leak private code and secrets.” Record PI-0031. Reported Oct. 8, 2025; updated Oct. 6, 2026. Rated under methodology v0.6. https://paperclipindex.com/incident/PI-0031