AI Risk Wire

Cases › security breach › LR-2026-0869

Greeter campaign exploiting Flowise AI agent platform (observed July-October 2026)

Who did it
Outside attacker
AI product
Flowise
How it was found
Outside researcher
Reported
9 Nov 2026
Severity
Minor
  1. Flowise is an open-source platform that businesses and developers use to build AI chatbots and autonomous agents. The sources name no operator, tools or permissions for the attacked instances.
  2. Attackers exploited a configuration vulnerability to swap JavaScript instructions into a running Flowise application. This let them run commands on the targeted servers without changing the stored configuration.
  3. Era Security did not establish that any genuine corporate cloud account was taken over. The attackers did find credentials, but those were planted in the researchers' test environment.
  4. Researchers at Era Security noticed the campaign when they recorded 4,972 identical messages that each said only 'hello'. They then reconstructed the hidden commands.

Source: Vision Times

What was done

Researchers urged organizations to secure the systems and resources that AI applications can reach.

Other stated action (Developer or vendor) · Monitoring added (Researcher or third party)

Risks AI system attacked or breached (54 incidents)

No source states: AI company and model, money lost or records, tools it had, company using the AI, sector.

Evidence

Sources (1)

  1. Hackers Exploit AI Chatbots to Hide Cyberattacks Behind Thousands of 'Hello' Messages - Vision Times · Vision Times · 2026-11-09
Show every field, with its source and grade

The AI system

Software around the model
Flowise
C one secondary source states it
Stage of use
in testing
D inferred by us from the described behaviour, reason shown
Whose system
company that built the AI
D inferred by us from the described behaviour, reason shown
What it was for
build AI chatbots and autonomous agents
C one secondary source states it

What happened

Earliest source we hold
2026-11-09
D inferred by us from the described behaviour, reason shown
Who caught it
an independent researcher or journalist
D inferred by us from the described behaviour, reason shown
Themes
CVE exploitation
D inferred by us from the described behaviour, reason shown
Who caused it
an outside attacker
D inferred by us from the described behaviour, reason shown
What went wrong
security breach
D inferred by us from the described behaviour, reason shown

Impact

Severity
minor
D inferred by us from the described behaviour, reason shown
Why this severity
No third party was touched. The credentials the attackers found were planted in the researchers' test environment, and no genuine corporate cloud account takeover was established.
D inferred by us from the described behaviour, reason shown

LR-2026-0869 · version 2 · published 2026-11-09 after automatic checks; not yet checked field by field by a person