{"answers":{"affected":"3 open source packages ship an affected version, including openharness-ai.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-56696 exists.","fix":"No fix has been published for CVE-2026-56696 yet. Limit exposure of the affected software until one is available.","what":"CVE-2026-56696 is a medium-severity code injection vulnerability in HKUDS OpenHarness, published on 23 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-2026-56696 and fix it if it is affected.\n\nWhat it is: CVE-2026-56696 is a medium-severity code injection vulnerability in HKUDS OpenHarness, published on 23 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-2026-56696 exists.\n\nAffected packages and fixed versions:\n- openharness-ai (PyPI): affected all versions up to 0.1.9; no fix listed\n- openharness-ai (PyPI): affected all versions up to 0.1.9; no fix listed\n- openharness-ai (PyPI): affected all versions up to 0.1.9; no fix listed\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-2026-56696/ (Markdown: https://insights.sbomify.com/CVE-2026-56696/index.md)","id":"CVE-2026-56696","markdown":"https://insights.sbomify.com/CVE-2026-56696/index.md","name":"CVE-2026-56696","record":{"aliases":["GHSA-24cw-228q-3rx9","PYSEC-2026-3880"],"analysis":{"component_type":"developer_tool","fix_type":"patch","impacts":["code_execution","privilege_escalation"],"network_reachable":"yes","non_default_config":false,"product_category":"AI agent framework","requires_auth":"low_privilege","summary":"Remote attackers can inject malicious Markdown into agent context files via slash commands, leading to persistent prompt injection and potential code execution.","user_interaction":"not_required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"VulnCheck","cpe":[],"cvss":{"score":5.3,"severity":"medium","source":"cna","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N","version":"4.0"},"cwes":[{"id":"CWE-862","name":"Missing Authorization"}],"description":"OpenHarness /issue and /pr_comments slash commands lack remote_invocable=False protection, allowing remote channel senders to write attacker-controlled Markdown into project context files. Admitted remote attackers can inject malicious content into .openharness/issue.md and .openharness/pr_comments.md files, which are subsequently injected into runtime system prompts, persistently influencing local agent behavior.","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":"OpenHarness - Prompt Injection via /issue and /pr_comments Slash Commands","id":"CVE-2026-56696","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"code_injection","year":"2026"},"n_packages":3,"n_references":3,"next":{"headline":"Nuxt - Open Redirect via Protocol-Relative Paths in reloadNuxtApp","id":"CVE-2026-56697"},"packages":[{"ecosystem":"PyPI","fixed":[],"introduced":["0"],"last_affected":["0.1.9"],"package":"openharness-ai","purl":null,"source":"GHSA-24cw-228q-3rx9"},{"ecosystem":"PyPI","fixed":[],"introduced":["0"],"last_affected":["0.1.9"],"package":"openharness-ai","purl":"pkg:pypi/openharness-ai","source":"GHSA-24cw-228q-3rx9"},{"ecosystem":"PyPI","fixed":[],"introduced":["0"],"last_affected":["0.1.9"],"package":"openharness-ai","purl":"pkg:pypi/openharness-ai","source":"PYSEC-2026-3880"}],"prev":{"headline":"OpenHarness - Cross-Session Disclosure via /resume and /summary Commands","id":"CVE-2026-56695"},"products":["OpenHarness"],"published":"2026-06-23","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":"2026-07-14","vendors":["HKUDS"]},"summary":"Remote attackers can inject malicious Markdown into agent context files via slash commands, leading to persistent prompt injection and potential code execution.","url":"https://insights.sbomify.com/CVE-2026-56696/"}