{"answers":{"affected":"2 open source packages ship an affected version, including atomic-agents-stack.","exploited":"There is no known exploitation of CVE-2026-91988 in the wild and no public exploit code.","fix":"Upgrade atomic-agents-stack to 1.1.0 or later.","what":"CVE-2026-91988 is a critical code injection vulnerability in dep0we atomic-agents-stack, published on 15 Sep 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-2026-91988 and fix it if it is affected.\n\nWhat it is: CVE-2026-91988 is a critical code injection vulnerability in dep0we atomic-agents-stack, published on 15 Sep 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-2026-91988 in the wild and no public exploit code.\n\nAffected packages and fixed versions:\n- atomic-agents-stack (PyPI): affected all versions; fixed in 1.1.0\n- atomic-agents-stack (PyPI): affected all versions; fixed in 1.1.0\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-2026-91988/ (Markdown: https://insights.sbomify.com/CVE-2026-91988/index.md)","id":"CVE-2026-91988","markdown":"https://insights.sbomify.com/CVE-2026-91988/index.md","name":"CVE-2026-91988","record":{"aliases":["GHSA-wr36-693x-8mgc","GHSA-xhcr-cqfr-m3hv"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"AI agent stack library","requires_auth":"none","summary":"Man-in-the-middle attackers can inject commands into HTTP MCP responses, leading to remote code execution on the agent host.","user_interaction":"not_required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"VulnCheck","cpe":[],"cvss":{"score":9.2,"severity":"critical","source":"cna","vector":"CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","version":"4.0"},"cwes":[{"id":"CWE-319","name":"Cleartext Transmission of Sensitive Information"}],"description":"atomic-agents-stack before 1.1.0 accepts cleartext HTTP schemes in the HTTP MCP server-registry backend factory, allowing network man-in-the-middle attackers to rewrite catalog responses. Attackers can inject arbitrary command and argument values that are spawned as local subprocesses by MCPClientPool to achieve code execution on the agent host.","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":false,"headline":"atomic-agents-stack before 1.1.0 Remote Code Execution via HTTP MCP","id":"CVE-2026-91988","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"code_injection","year":"2026"},"n_packages":2,"n_references":2,"next":{"headline":"atomic-agents-stack before 1.1.0 Path Traversal via dashboard serve.py","id":"CVE-2026-91989"},"packages":[{"ecosystem":"PyPI","fixed":["1.1.0"],"introduced":["0"],"last_affected":[],"package":"atomic-agents-stack","purl":null,"source":"GHSA-xhcr-cqfr-m3hv"},{"ecosystem":"PyPI","fixed":["1.1.0"],"introduced":["0"],"last_affected":[],"package":"atomic-agents-stack","purl":"pkg:pypi/atomic-agents-stack","source":"GHSA-xhcr-cqfr-m3hv"}],"prev":{"headline":"atomic-agents-stack before 1.1.0 Cost Guardrail Bypass via Unknown Model","id":"CVE-2026-91987"},"products":["atomic-agents-stack"],"published":"2026-09-15","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":"no","exploitation":"none","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-09-15","vendors":["dep0we"]},"summary":"Man-in-the-middle attackers can inject commands into HTTP MCP responses, leading to remote code execution on the agent host.","url":"https://insights.sbomify.com/CVE-2026-91988/"}