CWE-693Weakness · CWE-693

CVE-2026-60086

MEDIUM · 5.3 CVSS v3.1 Published 2026-07-10
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
62/100
Remediation priority · Elevated
Remotely reachable No privileges Zero-click 6 weeks old

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are classified as HIGH threat level and pass through unblocked to reach the model.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

PraisonAI before 4.6.78 has a prompt injection defense bypass where the protection mechanism only blocks threats classified as CRITICAL requiring 3+ detector families to match simultaneously. Single or double-vector prompt injections are classified as HIGH (not CRITICAL), allowing them to bypass the defense and reach the language model.

MitigationUpgrade to PraisonAI version 4.6.78 or later which addresses the threat classification threshold to block HIGH-level prompt injections.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
Low
Availability
None

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Identify PraisonAI installation and version
    Run 'pip show praisonai' or check your project's requirements.txt/poetry.lock for the installed PraisonAI package version
    Affected if The installed version is lower than 4.6.78 (e.g., 4.6.77, 4.6.0, 3.x.x)
  2. Confirm prompt injection protection is active
    Inspect your PraisonAI configuration or initialization code for settings related to prompt injection detection (look for terms like 'prompt_guard', 'injection_protection', 'security_filter', or similar security modules)
    Affected if Protection is enabled and uses detector families to classify threats
  3. Verify the threat classification threshold
    Examine the security configuration or code where detector family matches are evaluated - look for logic that only blocks threats when 3 or more detector families report a match
    Affected if The system only blocks threats flagged as CRITICAL and allows HIGH-level threats to pass through to the language model
  4. Test with a single-vector prompt injection
    Submit a basic prompt injection attempt (e.g., a simple jailbreak or system prompt override) through your PraisonAI deployment and observe whether it reaches the language model
    Affected if The injection reaches the LLM instead of being blocked by the protection system

You are affected if PraisonAI version is below 4.6.78 AND the prompt injection defense is active with a threshold requiring 3+ detector families to match, allowing HIGH-level single or double-vector injections to bypass the blocking mechanism.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Upgrade to PraisonAI version 4.6.78 or later which addresses the threat classification threshold to block HIGH-level prompt injections.

Recommended fix Moderate confidence

PraisonAI 4.6.78 or later

  1. Check current PraisonAI version using: pip show praisonai or pip list | grep praisonai
  2. Upgrade to version 4.6.78 or later using: pip install --upgrade praisonai>=4.6.78
  3. Verify the upgrade was successful by checking the installed version: pip show praisonai

Generated from the published advisory — verify against the referenced sources before acting.

Have this fixed Scoped from the published advisory
  • Consultation4.0 h
  • Implementation8.0 h
  • Testing12.0 h
  • Review / QA4.0 h
28.0 hours of engineering $4,760
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $7,616.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-60086 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-60086 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data