{"answers":{"affected":"3 open source packages ship an affected version, including praisonaiagents.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-61447 exists.","fix":"Upgrade praisonaiagents to 1.6.78 or later.","what":"CVE-2026-61447 is a critical code injection vulnerability in MervinPraison PraisonAI, published on 11 Jul 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-2026-61447 and fix it if it is affected.\n\nWhat it is: CVE-2026-61447 is a critical code injection vulnerability in MervinPraison PraisonAI, published on 11 Jul 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-61447 exists.\n\nAffected packages and fixed versions:\n- praisonaiagents (PyPI): affected all versions; fixed in 1.6.78\n- praisonaiagents (PyPI): affected all versions; fixed in 1.6.78\n- praisonaiagents (PyPI): affected all versions; fixed in 1.6.78\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-2026-61447/ (Markdown: https://insights.sbomify.com/CVE-2026-61447/index.md)","id":"CVE-2026-61447","markdown":"https://insights.sbomify.com/CVE-2026-61447/index.md","name":"CVE-2026-61447","record":{"aliases":["GHSA-2xv2-w8cq-5gxw","PYSEC-2026-4266"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["code_execution","data_read"],"network_reachable":"yes","non_default_config":false,"product_category":"Python AI library","requires_auth":"none","summary":"Attackers can execute arbitrary code and steal secrets by influencing LLM output in PraisonAI's CodeAgent due to missing sandboxing.","user_interaction":"not_required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"VulnCheck","cpe":[],"cvss":{"score":10,"severity":"critical","source":"cna","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H","version":"4.0"},"cwes":[{"id":"CWE-94","name":"Improper Control of Generation of Code"}],"description":"PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.","ecosystems":["PyPI"],"exploits":{"exploitdb":1,"first_seen":"2026-08-11","github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[{"date":"2026-08-11","kind":"exploitdb","ref":"52639","stars":null,"title":"PraisonAI praisonaiagents  1.6.77 - Remote Code Execution"}],"tier":"weaponised"},"has_fix":true,"headline":"PraisonAI before 1.6.78 Remote Code Execution via CodeAgent","id":"CVE-2026-61447","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"code_injection","year":"2026"},"n_packages":3,"n_references":2,"next":{"headline":"Parse Server 9.0.0 Stored XSS via malformed Content-Type","id":"CVE-2026-61448"},"packages":[{"ecosystem":"PyPI","fixed":["1.6.78"],"introduced":["0"],"last_affected":[],"package":"praisonaiagents","purl":null,"source":"GHSA-2xv2-w8cq-5gxw"},{"ecosystem":"PyPI","fixed":["1.6.78"],"introduced":["0"],"last_affected":[],"package":"praisonaiagents","purl":"pkg:pypi/praisonaiagents","source":"GHSA-2xv2-w8cq-5gxw"},{"ecosystem":"PyPI","fixed":["1.6.78"],"introduced":["0"],"last_affected":[],"package":"praisonaiagents","purl":"pkg:pypi/praisonaiagents","source":"PYSEC-2026-4266"}],"prev":{"headline":"PraisonAI before 1.6.78 Remote Code Execution via Plugin Auto-Discovery","id":"CVE-2026-61446"},"products":["PraisonAI"],"published":"2026-07-11","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":"CC BY 4.0","name":"PyPA Advisory Database","prefix":"PYSEC"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"},{"class":"attribution","licence":"GPL-2.0-or-later","name":"Exploit-DB"}],"ssvc":{"automatable":"yes","exploitation":"poc","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-07-13","vendors":["MervinPraison"]},"summary":"Attackers can execute arbitrary code and steal secrets by influencing LLM output in PraisonAI's CodeAgent due to missing sandboxing.","url":"https://insights.sbomify.com/CVE-2026-61447/"}