Vulnerability in pydantic-ai (CVE-2026-107293)
Summary
Vulnerability in pydantic-ai (CVE-2026-107293). Risk of unauthorized operations or information disclosure. Exploitable via ModelRetry. Mitigation: upgrade to 2.27.1 or later.
Original description
The description as published by the source.
Summary
Pydantic AI's OpenTelemetry instrumentation supports InstrumentationSettings(include_content=False) to exclude message content — user prompts, model completions, tool call arguments and responses — from exported telemetry, so that agents can be monitored without sending sensitive content to the observability backend.
Retry prompts — the feedback messages Pydantic AI sends back to the model when its output fails validation or an output validator raises ModelRetry — were not covered by this setting when they were not associated with a tool call, as with structured output modes that don't use tool calls (e.g. NativeOutput or PromptedOutput) and output validators applied to text output. Their full content was recorded on model request spans even with include_content=False. Since validation feedback can quote invalid values from the model's response, message content that the setting was configured to withhold could reach the telemetry backend.
Details
Retry prompts without an associated tool call were serialized into span message attributes (such as gen_ai.input.messages and pydantic_ai.all_messages) as regular text parts, and this path did not apply the include_content check that every other message part applies. Retry prompts tied to a tool call, and all other message content, were redacted correctly.
Impact
This does not grant an attacker any new access to the agent or its data: the content is only visible to whoever can read the export…
Source: GitHub Security Advisories (Global) NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-107293 has been found in pydantic-ai.
Attackers can target a specific entry point like ModelRetry over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: 5.3/10.
What to do: upgrade pydantic-ai to 2.27.1 or later.
If unsure, ask your IT team or search "pydantic-ai CVE-2026-107293" on the vendor's site.
CVE-2026-107293 (pydantic-ai) — CWE-212 / CVSS v3 5.3
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: ModelRetry / NativeOutput / PromptedOutput / gen_ai.input.messages
Patched: 2.27.1 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
A vulnerability (CWE-212) exists in pydantic-ai. Attackers reach the vulnerable code path via ModelRetry without authentication.
Check the vendor advisory for the affected versions of pydantic-ai. Attack surface: ModelRetry / NativeOutput / PromptedOutput / gen_ai.input.messages.
Severity: Medium (CVSS 5.3/10). Risk of unauthorized operations or information disclosure.
Update to 2.27.1.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'pydantic-ai' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'pydantic-ai' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
pydantic-aiを grep し、稼働しているサービス・バージョンを把握する。 -
2Apply patch patch
Upgrade pydantic-ai to 2.27.1ステージング環境で 2.27.1 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。
-
3Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。
Affected packages
References
- advisory github.com
- advisory nvd.nist.gov
- package github.com
- package pypi.org
- package pypi.org
- web github.com
- web github.com
- web github.com
- web github.com