{"answers":{"affected":"2 open source packages ship an affected version, including claude-agent-sdk.","exploited":"There is no known exploitation of CVE-2026-96620 in the wild and no public exploit code.","fix":"Upgrade claude-agent-sdk to 0.2.121 or later.","what":"CVE-2026-96620 is a critical command injection vulnerability in anthropics claude-agent-sdk-python, published on 16 Oct 2026. An attacker can exploit it over the internet without logging in, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-96620 and fix it if it is affected.\n\nWhat it is: CVE-2026-96620 is a critical command injection vulnerability in anthropics claude-agent-sdk-python, published on 16 Oct 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.\nExploitation: There is no known exploitation of CVE-2026-96620 in the wild and no public exploit code.\n\nAffected packages and fixed versions:\n- claude-agent-sdk (PyPI): affected all versions; fixed in 0.2.121\n- claude-agent-sdk (PyPI): affected all versions; fixed in 0.2.121\n\nTask:\n1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.\n2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2026-96620/ (Markdown: https://insights.sbomify.com/CVE-2026-96620/index.md)","id":"CVE-2026-96620","markdown":"https://insights.sbomify.com/CVE-2026-96620/index.md","name":"CVE-2026-96620","record":{"aliases":["GHSA-h4mw-j7qp-8mwm"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"Python SDK","requires_auth":"none","summary":"Attackers can execute arbitrary commands by injecting CLI flags via the resume option in the Claude Agent SDK.","user_interaction":"not_required","vuln_class":"command_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[],"cvss":{"score":9.2,"severity":"critical","source":"cna","vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","version":"4.0"},"cwes":[{"id":"CWE-88","name":"Improper Neutralization of Argument Delimiters in a Command"},{"id":"CWE-78","name":"Improper Neutralization of Special Elements used in an OS Command"},{"id":"CWE-20","name":"Improper Input Validation"}],"description":"Claude Agent SDK is a Python SDK for Claude Code. Prior to 0.2.121, the resume option is passed to the Claude CLI as a separate token without validation, so a dash-leading value is parsed as an independent CLI flag. An attacker can inject the --mcp-config flag to define a stdio MCP server, causing arbitrary command execution at CLI startup outside the SDK permission controls. The issue is exploitable when an application passes untrusted input as the session ID to resume. This issue is fixed in version 0.2.121.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"none_known"},"has_fix":true,"headline":"Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution","id":"CVE-2026-96620","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"command_injection","year":"2026"},"n_packages":2,"n_references":4,"next":{"headline":"Arcane: Container-registry credential exfiltration via URL repoint + test to attacker host","id":"CVE-2026-96626"},"packages":[{"ecosystem":"PyPI","fixed":["0.2.121"],"introduced":["0"],"last_affected":[],"package":"claude-agent-sdk","purl":null,"source":"GHSA-h4mw-j7qp-8mwm"},{"ecosystem":"PyPI","fixed":["0.2.121"],"introduced":["0"],"last_affected":[],"package":"claude-agent-sdk","purl":"pkg:pypi/claude-agent-sdk","source":"GHSA-h4mw-j7qp-8mwm"}],"prev":{"headline":"Hex exhausts memory and disk on oversized or compressed responses from an untrusted mirror","id":"CVE-2026-96618"},"products":["claude-agent-sdk-python"],"published":"2026-10-16","related":[],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"CC BY 4.0","name":"GitHub Advisory Database","prefix":"GHSA"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"}],"ssvc":{"automatable":"yes","exploitation":"none","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-10-21","vendors":["anthropics"]},"summary":"Attackers can execute arbitrary commands by injecting CLI flags via the resume option in the Claude Agent SDK.","url":"https://insights.sbomify.com/CVE-2026-96620/"}