{"answers":{"affected":"6 open source packages ship an affected version, including praisonaiagents, PraisonAI and praisonai.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-47395 exists.","fix":"Upgrade praisonaiagents to 1.6.40 or later.","what":"CVE-2026-47395 is a medium-severity server-side request forgery vulnerability in MervinPraison PraisonAI, published on 21 Jul 2026. It can only be exploited from the same machine or local network, and only if a user opens a file or follows a link."},"fix_prompt":"Check this codebase for CVE-2026-47395 and fix it if it is affected.\n\nWhat it is: CVE-2026-47395 is a medium-severity server-side request forgery vulnerability in MervinPraison PraisonAI, published on 21 Jul 2026. It can only be exploited from the same machine or local network, and only if a user opens a file or follows a link.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-47395 exists.\n\nAffected packages and fixed versions:\n- praisonaiagents (PyPI): affected all versions; fixed in 1.6.40\n- praisonaiagents (PyPI): affected all versions; fixed in 1.6.40\n- praisonaiagents (PyPI): affected all versions; fixed in 1.6.40\n- PraisonAI (PyPI): affected all versions; fixed in 4.6.40\n- praisonai (PyPI): affected all versions; fixed in 4.6.40\n- praisonai (PyPI): affected all versions; fixed in 4.6.40\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-2026-47395/ (Markdown: https://insights.sbomify.com/CVE-2026-47395/index.md)","id":"CVE-2026-47395","markdown":"https://insights.sbomify.com/CVE-2026-47395/index.md","name":"CVE-2026-47395","record":{"aliases":["GHSA-5cxw-77wg-jrf3","PYSEC-2026-2903","PYSEC-2026-2942"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["data_read","security_bypass"],"network_reachable":"adjacent_or_local","non_default_config":false,"product_category":"Python AI agent library","requires_auth":"none","summary":"Attacker-controlled prompt text triggers automatic URL fetching, allowing access to internal loopback resources and injecting data into model context.","user_interaction":"required","vuln_class":"ssrf"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[],"cvss":{"score":5.5,"severity":"medium","source":"cna","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N","version":"3.1"},"cwes":[{"id":"CWE-200","name":"Exposure of Sensitive Information to an Unauthorized Actor"}],"description":"PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:\u003chttp-or-https-url\u003e`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context. There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator's machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"weaponised"},"has_fix":true,"headline":"PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context","id":"CVE-2026-47395","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"ssrf","year":"2026"},"n_packages":6,"n_references":3,"next":{"headline":"PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset","id":"CVE-2026-47396"},"packages":[{"ecosystem":"PyPI","fixed":["4.6.40"],"introduced":["0"],"last_affected":[],"package":"PraisonAI","purl":null,"source":"GHSA-5cxw-77wg-jrf3"},{"ecosystem":"PyPI","fixed":["4.6.40"],"introduced":["0"],"last_affected":[],"package":"praisonai","purl":"pkg:pypi/praisonai","source":"GHSA-5cxw-77wg-jrf3"},{"ecosystem":"PyPI","fixed":["4.6.40"],"introduced":["0"],"last_affected":[],"package":"praisonai","purl":"pkg:pypi/praisonai","source":"PYSEC-2026-2903"},{"ecosystem":"PyPI","fixed":["1.6.40"],"introduced":["0"],"last_affected":[],"package":"praisonaiagents","purl":null,"source":"GHSA-5cxw-77wg-jrf3"},{"ecosystem":"PyPI","fixed":["1.6.40"],"introduced":["0"],"last_affected":[],"package":"praisonaiagents","purl":"pkg:pypi/praisonaiagents","source":"GHSA-5cxw-77wg-jrf3"},{"ecosystem":"PyPI","fixed":["1.6.40"],"introduced":["0"],"last_affected":[],"package":"praisonaiagents","purl":"pkg:pypi/praisonaiagents","source":"PYSEC-2026-2942"}],"prev":{"headline":"PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate","id":"CVE-2026-47394"},"products":["PraisonAI","praisonaiagents"],"published":"2026-07-21","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)"}],"ssvc":{"automatable":"no","exploitation":"poc","technical_impact":"partial"},"state":"PUBLISHED","updated":"2026-07-21","vendors":["MervinPraison"]},"summary":"Attacker-controlled prompt text triggers automatic URL fetching, allowing access to internal loopback resources and injecting data into model context.","url":"https://insights.sbomify.com/CVE-2026-47395/"}