CVE-2026-61439Public exploitNetwork attack vector

Prompt injection bypass via permissive default threshold

Published Jul 11, 2026 · Updated Jul 11, 2026

Prompt injection defense bypass in PraisonAI before 4.6.78 allows remote attackers to send single-vector prompts to downstream agents. InjectionDefense defaults block_threshold to CRITICAL, so one HIGH-level detector match is logged and forwarded unchanged unless three checks fire. The opt-in defense must process untrusted input; prompt or context disclosure and tool invocation depend on downstream agent capabilities.

CVSS severity8.7
High
EPSS probability0.43%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Prompt injection defense bypass in PraisonAI before 4.6.78 allows remote attackers to send single-vector prompts to downstream agents. InjectionDefense defaults block_threshold to CRITICAL, so one HIGH-level detector match is logged and forwarded unchanged unless three checks fire. The opt-in defense must process untrusted input; prompt or context disclosure and tool invocation depend on downstream agent capabilities.

The record

CVE
CVE-2026-61439
Published
Jul 11, 2026
Updated
Jul 11, 2026
Vendor
Mervin Praison
Product
PraisonAI
Classifications
CWE-1188, CWE-1287, CWE-116, CWE-693, T1190
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Jul 11, 2026CVE publishedPublication date reported by the CVE source.
  2. Jul 11, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=0 <4.6.78

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

Mervin Praison · PraisonAIversion=0 <4.6.78

Published CVSS scores

8.7VulnCheckCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
7.5VulnCheckCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitPublished

Weakness, pattern, technique

CWE-1188Initialization of a Resource with an Insecure Default
CWE-1287Improper Validation of Specified Type of Input
CWE-116Improper Encoding or Escaping of Output
CWE-693Protection Mechanism Failure
T1190Exploit Public-Facing Application

Public exploit references

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo