{"api_version":"1","generated_at":"2026-11-16T23:53:55+00:00","cve":"CVE-2026-83816","urls":{"html":"https://cve.report/CVE-2026-83816","api":"https://cve.report/api/cve/CVE-2026-83816.json","docs":"https://cve.report/api","cve_org":"https://www.cve.org/CVERecord?id=CVE-2026-83816","nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-83816"},"summary":{"title":"CodeWhale: exec_shell parallel-readonly classifier auto-approves fd/rg/git grep exec flags enabling silent RCE","description":"CodeWhale is a DeepSeek and MiMo coding agent for the terminal. Prior to 0.9.0, the ExecShellTool::approval_requirement_for path used is_parallel_readonly_command to downgrade commands to automatic approval based on a flag-stripped command allowlist. The allowlist treated fd, rg, and git grep as read-only even when fd -x or fd --exec, rg --pre, or git grep --open-files-in-pager selected an external program. registered_tool_approval_required returned without displaying a prompt for that automatic classification, and the later command-safety check also treated the base utilities as safe. Attacker-controlled content that influenced an agent tool call could therefore cause arbitrary program execution on the developer host without the approval promised by the default interactive profile, resulting in unauthorized access, modification, or disruption. This issue is fixed in version 0.9.0.","state":"PUBLISHED","assigner":"GitHub_M","published_at":"2026-11-16 19:17:53","updated_at":"2026-11-16 22:18:25"},"problem_types":["CWE-78","CWE-863","CWE-78 CWE-78: Improper Neutralization of Special Elements used in an OS Command","CWE-863 CWE-863: Incorrect Authorization"],"metrics":[{"version":"3.1","source":"security-advisories@github.com","type":"Secondary","score":"8.1","severity":"HIGH","vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","data":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","baseScore":8.1,"baseSeverity":"HIGH","attackVector":"NETWORK","attackComplexity":"HIGH","privilegesRequired":"NONE","userInteraction":"NONE","scope":"UNCHANGED","confidentialityImpact":"HIGH","integrityImpact":"HIGH","availabilityImpact":"HIGH"}},{"version":"3.1","source":"CNA","type":"DECLARED","score":"8.1","severity":"HIGH","vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","data":{"attackComplexity":"HIGH","attackVector":"NETWORK","availabilityImpact":"HIGH","baseScore":8.1,"baseSeverity":"HIGH","confidentialityImpact":"HIGH","integrityImpact":"HIGH","privilegesRequired":"NONE","scope":"UNCHANGED","userInteraction":"NONE","vectorString":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","version":"3.1"}}],"references":[{"url":"https://github.com/codewhale-hq/Codewhale/releases/tag/v0.9.0","name":"https://github.com/codewhale-hq/Codewhale/releases/tag/v0.9.0","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/codewhale-hq/Codewhale/commit/208421b9d23d81cea3311a1eeb2a2ea81d637686","name":"https://github.com/codewhale-hq/Codewhale/commit/208421b9d23d81cea3311a1eeb2a2ea81d637686","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/codewhale-hq/Codewhale/security/advisories/GHSA-3mgh-93r5-r7jf","name":"https://github.com/codewhale-hq/Codewhale/security/advisories/GHSA-3mgh-93r5-r7jf","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-83816","name":"CVE Program record","refsource":"CVE.ORG","tags":["canonical"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-83816","name":"NVD vulnerability detail","refsource":"NVD","tags":["canonical","analysis"]}],"affected":[{"source":"CNA","vendor":"codewhale-hq","product":"CodeWhale","version":"affected < 0.9.0","platforms":[]}],"timeline":[],"solutions":[],"workarounds":[],"exploits":[],"credits":[],"nvd_cpes":[],"vendor_comments":[],"enrichments":{"kev":null,"epss":null,"legacy_qids":[]},"source_records":{"cve_program":{"containers":{"adp":[{"metrics":[{"other":{"content":{"id":"CVE-2026-83816","options":[{"Exploitation":"none"},{"Automatable":"no"},{"Technical Impact":"total"}],"role":"CISA Coordinator","timestamp":"2026-11-16T21:21:32.272607Z","version":"2.0.3"},"type":"ssvc"}}],"providerMetadata":{"dateUpdated":"2026-11-16T21:21:35.809Z","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","shortName":"CISA-ADP"},"title":"CISA ADP Vulnrichment"}],"cna":{"affected":[{"product":"CodeWhale","vendor":"codewhale-hq","versions":[{"status":"affected","version":"< 0.9.0"}]}],"descriptions":[{"lang":"en","value":"CodeWhale is a DeepSeek and MiMo coding agent for the terminal. Prior to 0.9.0, the ExecShellTool::approval_requirement_for path used is_parallel_readonly_command to downgrade commands to automatic approval based on a flag-stripped command allowlist. The allowlist treated fd, rg, and git grep as read-only even when fd -x or fd --exec, rg --pre, or git grep --open-files-in-pager selected an external program. registered_tool_approval_required returned without displaying a prompt for that automatic classification, and the later command-safety check also treated the base utilities as safe. Attacker-controlled content that influenced an agent tool call could therefore cause arbitrary program execution on the developer host without the approval promised by the default interactive profile, resulting in unauthorized access, modification, or disruption. This issue is fixed in version 0.9.0."}],"metrics":[{"cvssV3_1":{"attackComplexity":"HIGH","attackVector":"NETWORK","availabilityImpact":"HIGH","baseScore":8.1,"baseSeverity":"HIGH","confidentialityImpact":"HIGH","integrityImpact":"HIGH","privilegesRequired":"NONE","scope":"UNCHANGED","userInteraction":"NONE","vectorString":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","version":"3.1"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-78","description":"CWE-78: Improper Neutralization of Special Elements used in an OS Command","lang":"en","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-863","description":"CWE-863: Incorrect Authorization","lang":"en","type":"CWE"}]}],"providerMetadata":{"dateUpdated":"2026-11-16T18:57:48.606Z","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M"},"references":[{"name":"https://github.com/codewhale-hq/Codewhale/security/advisories/GHSA-3mgh-93r5-r7jf","tags":["x_refsource_CONFIRM"],"url":"https://github.com/codewhale-hq/Codewhale/security/advisories/GHSA-3mgh-93r5-r7jf"},{"name":"https://github.com/codewhale-hq/Codewhale/commit/208421b9d23d81cea3311a1eeb2a2ea81d637686","tags":["x_refsource_MISC"],"url":"https://github.com/codewhale-hq/Codewhale/commit/208421b9d23d81cea3311a1eeb2a2ea81d637686"},{"name":"https://github.com/codewhale-hq/Codewhale/releases/tag/v0.9.0","tags":["x_refsource_MISC"],"url":"https://github.com/codewhale-hq/Codewhale/releases/tag/v0.9.0"}],"source":{"advisory":"GHSA-3mgh-93r5-r7jf","discovery":"UNKNOWN"},"title":"CodeWhale: exec_shell parallel-readonly classifier auto-approves fd/rg/git grep exec flags enabling silent RCE"}},"cveMetadata":{"assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","assignerShortName":"GitHub_M","cveId":"CVE-2026-83816","datePublished":"2026-11-16T18:55:40.450Z","dateReserved":"2026-08-31T23:04:48.173Z","dateUpdated":"2026-11-16T21:21:35.809Z","state":"PUBLISHED"},"dataType":"CVE_RECORD","dataVersion":"5.2"},"nvd":{"publishedDate":"2026-11-16 19:17:53","lastModifiedDate":"2026-11-16 22:18:25","problem_types":["CWE-78","CWE-863","CWE-78 CWE-78: Improper Neutralization of Special Elements used in an OS Command","CWE-863 CWE-863: Incorrect Authorization"],"metrics":{"cvssMetricV31":[{"source":"security-advisories@github.com","type":"Secondary","cvssData":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","baseScore":8.1,"baseSeverity":"HIGH","attackVector":"NETWORK","attackComplexity":"HIGH","privilegesRequired":"NONE","userInteraction":"NONE","scope":"UNCHANGED","confidentialityImpact":"HIGH","integrityImpact":"HIGH","availabilityImpact":"HIGH"},"exploitabilityScore":2.2,"impactScore":5.9}],"ssvcV203":[{"source":"134c704f-9b21-4f2e-91b3-4a467353bcc0","ssvcData":{"timestamp":"2026-11-16T21:21:32.272607Z","id":"CVE-2026-83816","options":[{"exploitation":"none"},{"automatable":"no"},{"technicalImpact":"total"}],"role":"CISA Coordinator","version":"2.0.3"}}]},"configurations":[]},"legacy_mitre":{"record":{"CveYear":"2026","CveId":"83816","Ordinal":"1","Title":"CodeWhale: exec_shell parallel-readonly classifier auto-approves","CVE":"CVE-2026-83816","Year":"2026"},"notes":[{"CveYear":"2026","CveId":"83816","Ordinal":"1","NoteData":"CodeWhale is a DeepSeek and MiMo coding agent for the terminal. Prior to 0.9.0, the ExecShellTool::approval_requirement_for path used is_parallel_readonly_command to downgrade commands to automatic approval based on a flag-stripped command allowlist. The allowlist treated fd, rg, and git grep as read-only even when fd -x or fd --exec, rg --pre, or git grep --open-files-in-pager selected an external program. registered_tool_approval_required returned without displaying a prompt for that automatic classification, and the later command-safety check also treated the base utilities as safe. Attacker-controlled content that influenced an agent tool call could therefore cause arbitrary program execution on the developer host without the approval promised by the default interactive profile, resulting in unauthorized access, modification, or disruption. This issue is fixed in version 0.9.0.","Type":"Description","Title":"CodeWhale: exec_shell parallel-readonly classifier auto-approves"}]}}}