PraisonAI: Prompt-injection defense blocks only when 3+ detector families fire simultaneously; realistic single-vector injections pass through unblocked

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

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

EPSS

• CVE-2026-60086: 0.27% estimated exploitation activity in the next 30 days; percentile 18.83 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary PraisonAI's opt-in prompt-injection defense (enableinjectiondefense()) only blocks at ThreatLevel.CRITICAL, which requires three or more distinct detector families to match simultaneously. A realistic single- or double-vector prompt injection (e.g. "Ignore all previous instructions…") is classified HIGH and passes through unmodified. The documented HIGH "sanitize" behavior is not implemented. Root cause scantext sets blocked = (level = ThreatLevel.CRITICAL) and not istrusted (src/praisonai/praisonai/security/injection.py, around line 236). The severity ladder (around lines 223-233) reaches CRITICAL only when 3+ detector families fire; 1-2 checks yield HIGH, which never blocks. The ThreatLevel docstring declares HIGH = 2

Log + warn; sanitize, but no code path mutates the text at this level. Proof of concept Impact When the defense is enabled, ordinary prompt-injection payloads still reach the model and tools. An attacker only needs to avoid tripping 3+ regex families…

Published by the source

8 Oct 2026, 19:39 UTC

Last modified by the source

15 Oct 2026, 14:56 UTC

Source last checked

26 Oct 2026, 13:55 UTC

1. Revision 3 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-4r3p-w3mc-5v34

2. Revision 2 · amended · 24 Oct 2026

   Amended from osv record GHSA-4r3p-w3mc-5v34

3. Revision 1 · created · 23 Oct 2026

   Published from ghsa record GHSA-4r3p-w3mc-5v34

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-60086

Advisory: PraisonAI: Prompt-injection defense blocks only when 3+ detector families fire simultaneously; realistic single-vector injections pass through unblocked
IDs: CVE-2026-60086, GHSA-4r3p-w3mc-5v34
Record: https://patchnext.com/advisories/cve-2026-60086 (revision 3, source checked 26 Oct 2026, 13:55 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Medium (CVSS 5.3)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: praisonai 4.6.78. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI praisonai: affected <= 4.6.77; fixed in 4.6.78

## Suggested inspection (read-only)
- `python -m pip show praisonai`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on praisonai.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://github.com/advisories/GHSA-4r3p-w3mc-5v34 (GitHub-reviewed advisory GHSA-4r3p-w3mc-5v34 lists affected ranges: PyPI praisonai >=0 <=4.6.77)
- Verified: https://osv.dev/vulnerability/GHSA-4r3p-w3mc-5v34 (OSV record GHSA-4r3p-w3mc-5v34 lists affected ranges: PyPI praisonai >=0 <4.6.78 (fixed))

Commands are suggestions: review each one before running it.