// Security Advisory Triage
PraisonAI 4.6.78 patches YAML injection in code generator
GitHub advisories — pip · published 2026-10-09 13:20 UTC
WHAT CHANGEDCVE-2026-61433 published 8 October 2026. PraisonAI versions before 4.6.78 embed unescaped YAML fields directly into generated Python source code in the API deploy code generator. Severity rated high. First patched version is 4.6.78.
WHY IT MATTERSAn attacker controlling YAML input can inject arbitrary Python code that executes when the generated deployment code runs. This is a code generation vulnerability in an AI framework SDK — the generated code itself is the attack surface.
WHAT TO DOUpgrade praisonai to 4.6.78 or later if you use the API deploy code generator. If you cannot upgrade immediately, audit any generated deployment code for unescaped YAML content and do not run code generated from untrusted YAML sources.
Model-reported confidence 88% (not measured accuracy)
Primary source ↗
written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
+ghsa_id: GHSA-79fv-7hq9-w7xg +summary: PraisonAI: API deploy code generator embeds unescaped YAML fields into Python source +severity: high +published_at: 2026-10-08T19:36:29Z +cve_id: CVE-2026-61433 +vulnerabilities[].package.name: praisonai +vulnerabilities[].first_patched_version: 4.6.78
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
| triage verdict | MATERIAL at 0.92, needed 0.5 |
|---|---|
| triage reasoning | PraisonAI is an AI agent framework whose code generator embeds untrusted YAML into executable Python. This affects services using the SDK. |
| signals | AI framework SDK affected · code generation vulnerability · unescaped YAML injection into Python source · high severity · first patched version available · new advisory entry |
| suppression | — |
| triage model | anthropic/claude-haiku-4.5 ($0.00000) |
| writer model | anthropic/claude-sonnet-4.5 ($0.00000) |