CVE Professor — Güvenlik Açığı Takip & Analiz
›
CVE-2026-107291

CWE-212 · CWE-532

ORTA CVSS 4.3 ⚡ EPSS 0.6% NVD

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.6 and 2.44.0, OpenTelemetry instrumentation configured with InstrumentationSettings(include_content=False) can still export sensitive agent content through exception.message and exception.stacktrace events, error status descriptions, and model_request_parameters containing instructions or the prompted_output_template. The exposed data is available to readers of the configured telemetry backend and can include tool feedback, provider error bodies, runtime instructions, and structured-output templates even though message attributes are redacted. This issue does not grant new access to agent data, and deployments that do not use include_content=False are not affected by the setting bypass. This issue is fixed in versions 1.107.6 and 2.44.0.

Yayınlanma 08.10.2026
ISO Tarih 2026-10-08
CVSS Sürüm v3.1
Kaynak NVD
CVSS v3.1 Metrikleri
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N
Attack Vector Network AV:N
Attack Complexity Low AC:L
Privileges Req. Low PR:L
User Interaction None UI:N
Scope Unchanged S:U
Confidentiality Low C:L
Integrity None I:N
Availability None A:N
EPSS — Exploit Olasılık Skoru
0.6%
30 günlük olasılık
Tüm CVElerin 50. yüzdeliğinde — Bu açığın istismar edilme ihtimali çoğu CVEden yüksek.
AI Güvenlik Analizi

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CVE-2026-107291
CVSS 4.3/10 · ORTA · 08.10.2026
CWE: CWE-212, CWE-532
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🎯 AÇIK NEDİR?
Açıklama: Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.6 and 2.44.0, OpenTelemetry instrumentation configured with InstrumentationSettings(include_content=False) can still export sensitive agent content through exception.message and exception.stacktrace events, error status descriptions, and model_request_parameters containing …
Etkilenen: pydantic:pydantic_ai

⚡ SALDIRI ZİNCİRİ
İnternet üzerinden uzaktan | düşük yetkili hesap | kullanıcı etkileşimi YOK | düşük karmaşıklık.

🌍 GERÇEK DÜNYA ETKİSİ

🛡️ ÇÖZÜM VE MİTİGASYON
→ pydantic:pydantic_ai için üretici güvenlik güncellemesini uygula.
→ WAF kuralı ekle, anormal trafik için IDS alert oluştur.

⚠️ ACİLİYET
📋 Rutin güncelleme (30 gün)

────────────────────────────────────────
[Kural Tabanlı Analiz] [💡 config.json dosyasına ai_key (Claude: sk-ant-... veya Groq: gsk_...) ekleyerek gerçek AI analizi kullanabilirsiniz]

[⚠️ AI key mevcut ancak istek başarısız — kural tabanlı analiz kullanıldı]

Hedef Keşif Sorguları

FOFA Sorgusu

app="pydantic pydantic_ai"
CVSS Skoru
4.3 / 10 · CVSS ORTA
Zayıflık Türleri (CWE)
CWE-212 CWE-532
Etkilenen Ürünler (1)
pydantic:pydantic_ai (tüm sürümler)
Referanslar (6)
github.com patch
github.com patch
github.com patch
github.com patch
github.com patch
github.com patch advisory
İlgili CVE'ler
8.8
CVE-2026-91879
Dell Terraform for ObjectScale and Powerstore, versions prior to 1.1.1 (ObjectScale) and versions 1.2.1 throug
8.8
CVE-2026-54145
OpenHuman is an open-source agent harness available as a desktop application and Rust library. In affected ver
8.8
CVE-2026-92918
admin3 through 3.0.0 persists user session tokens in the audit log event body when publishing UserLoggedIn dom
8.8
CVE-2026-85094
The Canva Android App before 2.376.0 did not restrict the headers returned to an external origin running in a
8.8
CVE-2026-85174
SiYuan before v3.8.2 logs API tokens from query parameters in plaintext to an accessible log file when full-te