CVE-2026-60086
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 · uneditedPraisonAI 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 confidencePraisonAI 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.
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 checksWork through these to decide whether this CVE applies to you.
-
Identify PraisonAI installation and versionRun 'pip show praisonai' or check your project's requirements.txt/poetry.lock for the installed PraisonAI package versionAffected if The installed version is lower than 4.6.78 (e.g., 4.6.77, 4.6.0, 3.x.x)
-
Confirm prompt injection protection is activeInspect 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
-
Verify the threat classification thresholdExamine 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 matchAffected if The system only blocks threats flagged as CRITICAL and allows HIGH-level threats to pass through to the language model
-
Test with a single-vector prompt injectionSubmit 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 modelAffected 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.
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 · scopedUpgrade to PraisonAI version 4.6.78 or later which addresses the threat classification threshold to block HIGH-level prompt injections.
PraisonAI 4.6.78 or later
- Check current PraisonAI version using: pip show praisonai or pip list | grep praisonai
- Upgrade to version 4.6.78 or later using: pip install --upgrade praisonai>=4.6.78
- 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.
- Consultation4.0 h
- Implementation8.0 h
- Testing12.0 h
- Review / QA4.0 h
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 locallyCheck 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 sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-60086 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
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.
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.
- 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