Vulnerability in claude-agent-sdk (CVE-2026-96620)
Summary
Vulnerability in claude-agent-sdk (CVE-2026-96620). Risk of unauthorized operations or information disclosure. Exploitable via resume. Mitigation: upgrade to 0.2.121 or later.
Original description
The description as published by the source.
The Claude Agent SDK for Python passed the resume option to the Claude CLI without validation, allowing a value beginning with - to be interpreted as a separate CLI flag. An attacker who controlled the resume value could inject an --mcp-config flag defining a stdio MCP server, resulting in arbitrary command execution at CLI startup that bypassed the SDK's permission controls. Exploitation required an application to pass untrusted input as the session ID to resume.
Users are advised to update to the latest version of the claude-agent-sdk package.
Thank you to hackerone.com/moamenmahmood for reporting this issue.
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-2026-96620 has been found in claude-agent-sdk.
Attackers can target a specific entry point like resume over the network to misuse the product.
Risk of unauthorized operations or information disclosure.
What to do: upgrade claude-agent-sdk to 0.2.121 or later.
If unsure, ask your IT team or search "claude-agent-sdk CVE-2026-96620" on the vendor's site.
CVE-2026-96620 (claude-agent-sdk) — CWE-20
Attack surface: resume
Patched: 0.2.121 — 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-20) exists in claude-agent-sdk. Attackers reach the vulnerable code path via resume.
Check the vendor advisory for the affected versions of claude-agent-sdk. Attack surface: resume.
Severity: ?. Risk of unauthorized operations or information disclosure.
Update to 0.2.121.
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 'claude-agent-sdk' . 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 'claude-agent-sdk' . | 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
claude-agent-sdk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 claude-agent-sdk to 0.2.121ステージング環境で 0.2.121 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。