Cases › security breach › LR-2026-0313

Mercor breached through compromised LiteLLM PyPI releases (TeamPCP)

Preliminary Why: Publisher not yet named · subject to change

Status: no action reported

Severity moderate

Reported 25 Jun 2026

No source states: loss or records, developer and model, agent tool, could do, deployer, industry.

Severity moderate: Data of others touched (sensitive information of experts) with a bounded scope stated: only a very limited subset of nearly five million experts had sensitive information affected.

Mercor, which works with AI experts and customers, was affected by a supply-chain attack involving LiteLLM, a commonly used open-source tool. A malicious actor published compromised versions of LiteLLM designed to exfiltrate credentials from any system that installed them. Mercor's security team determined that the company was affected during the relevant timeframe and took action to contain unauthorized activity. The company investigated with outside forensics experts and law enforcement. Of its nearly five million experts, only a very limited subset had sensitive information affected, and the company reported no evidence that this data had been used fraudulently. Notifications with identity protection offers were sent to affected individuals, and the company audited third-party dependencies and rotated credentials and access keys.

What happened

1 · What it was doingMercor relied on LiteLLM, a commonly used open-source tool, when a supply-chain attack involving it reached the company.

2 · What went wrongA malicious actor published compromised LiteLLM versions designed to exfiltrate credentials from any system that installed them.

3 · What it reached or didOf nearly five million experts, only a very limited subset had sensitive information affected.

4 · How it was caughtMercor's security team determined it was affected and immediately acted to contain unauthorized activity.

What was done

No source states an action or fix.

Risks

Supply-chain compromise
Primary24 incidents
Rising: 4 vs 0.2 a week

Credential and privilege abuse
Also37 incidents

Read from the sources; not yet reviewed by a person.

Controls

Not yet read for controls. Controls that mitigate the primary risk:

Harness

Sandboxed code execution

Application

Signed and verified components · Vetting of plug-ins, skills and dependencies · AI bill of materials · Vulnerability scanning of AI components · Model provenance checks · Least-privilege access for the agent

Infrastructure / target

Secrets scanning

Similar incidents

Compromised LiteLLM PyPI packages deliver credential-stealing malware2026-03-24

Mercor data breach via LiteLLM supply-chain compromise (April 2026)2026-04-23

All cases of this kind ›

Evidence

No source states: when it was found, how many records were exposed, the direct loss, a count of the other parties affected, any court case, the cause, what set it off, what was done.

Show the full account: 6 items from the primary sources

What happened, in order

late March 2026 Mercor was affected by a supply-chain attack involving LiteLLM.
March A malicious actor published compromised LiteLLM versions designed to exfiltrate credentials.
June 25 and June 26 Mercor began notifying affected experts directly.

Not dated in the sources:

Mercor's security team determined it was affected and immediately acted to contain unauthorized activity.
Mercor worked with outside forensics experts, industry peers and law enforcement during the investigation.
The investigation was completed.

Show every field, with its source and grade

What happened

When it happened

2026-03-01

C one secondary source states it

Earliest source we hold

2026-06-25