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-0030

ForcedLeak: web form submissions could make Salesforce Agentforce leak CRM lead data

Noma Security found that instructions hidden in a Web-to-Lead form submission could make Salesforce's Agentforce agent list lead email addresses and embed them in an image link when an employee later asked about the lead. The chain worked partly because an expired domain on Salesforce's allow-list could be bought for a few dollars. Salesforce patched the flaw and began enforcing trusted-URL allow-lists from Sept. 8, 2025.

Reported Sept. 25, 2025Happened on July 28, 2025Discovered July 28, 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

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

  1. researchForcedLeak: AI agent risks exposed in Salesforce AgentforceNoma Security · Sept. 25, 2025noma.security/blog/forcedleak-agent-risks-exposed-in-salesforce-agentforce
  2. newsPrompt injection – and a $5 domain – trick Salesforce Agentforce into leaking salesThe Register · Sept. 26, 2025theregister.com/software/2025/09/26/salesforce-agentforce-tricked-into-leaking…
  3. newsSalesforce patches critical ForcedLeakThe Hacker News · Sept. 25, 2025thehackernews.com/2025/09/salesforce-patches-critical-forcedleak.html
  4. newsVulnerability in Salesforce AI could be tricked into leaking CRM dataCSO Online · Sept. 25, 2025csoonline.com/article/4063044/vulnerability-in-salesforce-ai-could-be-tricked-i…

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 read CRM data it could access and followed injected instructions to send it out; inside its 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

No exploitation or external harm was reported from this controlled test; Salesforce did not say whether any had occurred. Control level 2 reflects injected instructions obeyed within permissions.

The scales

Effect on the index

It does not count toward the Sept. 29 reading

The reading for the week to Sept. 29, 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. 3 other records behind the reading for that week.

The arithmetic
The reading for the week of Sept. 29, 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
Sept. 29, 20253Control failures only
Oct. 6, 20253Control failures only
Oct. 13, 20253Control failures only
Oct. 20, 20252Control failures only

Recalculated backcasts, not readings published at the time.

Revisions

What we changed

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

  1. v6
    Oct. 6, 2026

    Ratings confirmed by the editor.

  2. v5
    Oct. 3, 2026

    Audit corrections: event and discovery dated 28 Jul 2025, when Noma found and reported the flaw (its disclosure timeline). Status note added: Salesforce confirmed patches and re-secured the expired domain but declined to say whether the flaw was exploited or customer data affected (The Register, 26 Sep 2025), which the harm note and rationale now say. The Hacker News and CSO Online dated; Noma and Register links updated to their canonical URLs. Ratings unchanged.

  3. v4
    Oct. 2, 2026

    Report date moved from 2025-09-26 to 2025-09-25: Noma Security's ForcedLeak disclosure was published 25 Sep 2025.

  4. v3
    Oct. 2, 2026

    Added first-hand sources: Noma Security's ForcedLeak disclosure.

  5. v2
    Sept. 30, 2026

    Rated: impact not reported; control type instruction violation.

  6. v1
    Sept. 30, 2026

    Backfilled from public reporting.

Cite and share

Use this record

Citation

Paperclip Index. “ForcedLeak: web form submissions could make Salesforce Agentforce leak CRM lead data.” Record PI-0030. Reported Sept. 25, 2025; updated Oct. 6, 2026. Rated under methodology v0.6. https://paperclipindex.com/incident/PI-0030