{"answers":{"affected":"2 open source packages ship an affected version, including PraisonAI and praisonai.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-56075 exists.","fix":"Upgrade PraisonAI to 4.5.128 or later.","what":"CVE-2026-56075 is a high-severity command injection vulnerability in PraisonAI, published on 18 Jun 2026. Any signed-in user can exploit it over the network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-56075 and fix it if it is affected.\n\nWhat it is: CVE-2026-56075 is a high-severity command injection vulnerability in PraisonAI, published on 18 Jun 2026. Any signed-in user can exploit it over the network, with no action from the victim.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-56075 exists.\n\nAffected packages and fixed versions:\n- PraisonAI (PyPI): affected all versions; fixed in 4.5.128\n- praisonai (PyPI): affected all versions; fixed in 4.5.128\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-2026-56075/ (Markdown: https://insights.sbomify.com/CVE-2026-56075/index.md)","id":"CVE-2026-56075","markdown":"https://insights.sbomify.com/CVE-2026-56075/index.md","name":"CVE-2026-56075","record":{"aliases":["GHSA-gx4r-3wg8-9w5x","GHSA-qwgj-rrpj-75xm"],"analysis":{"component_type":"web_application","fix_type":"upgrade","impacts":["code_execution","security_bypass"],"network_reachable":"yes","non_default_config":false,"product_category":"AI agent framework","requires_auth":"low_privilege","summary":"Authenticated attackers can execute arbitrary shell commands by bypassing approval gates in PraisonAI, leading to remote code execution.","user_interaction":"not_required","vuln_class":"command_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"VulnCheck","cpe":[],"cvss":{"score":8.7,"severity":"high","source":"cna","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","version":"4.0"},"cwes":[{"id":"CWE-863","name":"Incorrect Authorization"}],"description":"PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing the manual approval gate and insufficient command sanitization blocklists.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"weaponised"},"has_fix":false,"headline":"PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override","id":"CVE-2026-56075","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"command_injection","year":"2026"},"n_packages":2,"n_references":2,"next":{"headline":"PraisonAI - Cross-Origin Agent Execution via Hardcoded Wildcard CORS and Missing Authentication on AGUI Endpoint","id":"CVE-2026-56076"},"packages":[{"ecosystem":"PyPI","fixed":["4.5.128"],"introduced":["0"],"last_affected":[],"package":"PraisonAI","purl":null,"source":"GHSA-qwgj-rrpj-75xm"},{"ecosystem":"PyPI","fixed":["4.5.128"],"introduced":["0"],"last_affected":[],"package":"praisonai","purl":"pkg:pypi/praisonai","source":"GHSA-qwgj-rrpj-75xm"}],"prev":{"headline":"PraisonAI - Tool Approval Cache Bypass via Coarse-Grained Caching","id":"CVE-2026-56074"},"products":["PraisonAI"],"published":"2026-06-18","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":"poc","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-10-08","vendors":["PraisonAI"]},"summary":"Authenticated attackers can execute arbitrary shell commands by bypassing approval gates in PraisonAI, leading to remote code execution.","url":"https://insights.sbomify.com/CVE-2026-56075/"}