{"id":"CVE-2026-53845","aliases":["EUVD-2026-37147","GHSA-68xw-r643-9p5w","GHSA-r7vv-6763-m739"],"status":"published","title":"OpenClaw \u003c 2026.5.6 - Skill-Command Dispatch Hook Bypass via Before-Tool-Call Hook Skipping","description":"OpenClaw before 2026.5.6 contains a hook bypass vulnerability where skill commands routed through the affected dispatch path skip before-tool-call hook coverage. Attackers can exploit this by sending skill commands through the vulnerable dispatch path to bypass hook-based auditing and policy enforcement mechanisms.","severity":{"version":"4.0","score":2.3,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N","level":"low","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-09","score":0.00185,"percentile":0.08086,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-693"],"published":"2026-06-16T18:04:56Z","modified":"2026-10-28T02:31:06Z","fixes":[{"ecosystem":"npm","package":"openclaw","fixed_in":["2026.5.6"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"npm","package":"openclaw","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"2026.5.5"},{"fixed":"2026.5.6"}]}]},{"source":"osv","ecosystem":"npm","package":"openclaw","ranges":[{"type":"SEMVER","events":[{"introduced":"0"},{"fixed":"2026.5.6"}]}]}],"products":[{"vendor":"openclaw","product":"openclaw"}],"references":[{"url":"https://github.com/openclaw/openclaw/security/advisories/GHSA-68xw-r643-9p5w","tags":["vendor-advisory","Vendor Advisory","advisory","web"]},{"url":"https://www.vulncheck.com/advisories/openclaw-skill-command-dispatch-hook-bypass-via-before-tool-call-hook-skipping","tags":["third-party-advisory","Third Party Advisory","advisory","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-53845","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-68xw-r643-9p5w"},{"url":"https://github.com/advisories/GHSA-r7vv-6763-m739"},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/53xxx/CVE-2026-53845.json","tags":["advisory"]},{"url":"https://github.com/openclaw/openclaw","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2026-53845","title":"OpenClaw \u003c 2026.5.6 - Skill-Command Dispatch Hook Bypass via Before-Tool-Call Hook Skipping","description":"OpenClaw before 2026.5.6 contains a hook bypass vulnerability where skill commands routed through the affected dispatch path skip before-tool-call hook coverage. Attackers can exploit this by sending skill commands through the vulnerable dispatch path to bypass hook-based auditing and policy enforcement mechanisms.","status":"published","published":"2026-06-16T18:04:56.803Z","modified":"2026-06-16T18:55:41.789Z","cvss":[{"version":"4.0","score":2.3,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N","level":"low","assessor":"cna"},{"version":"3.1","score":4.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N","level":"medium","assessor":"cna"}],"cwes":["CWE-693"],"updated_at":"2026-11-02T14:20:00.11477Z"}],"euvd":[{"id":"EUVD-2026-37147","description":"OpenClaw before 2026.5.6 contains a hook bypass vulnerability where skill commands routed through the affected dispatch path skip before-tool-call hook coverage. Attackers can exploit this by sending skill commands through the vulnerable dispatch path to bypass hook-based auditing and policy enforcement mechanisms.","status":"published","published":"2026-06-16T18:04:56Z","modified":"2026-06-16T18:55:41Z","cvss":[{"version":"4.0","score":2.3,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N","level":"low"}],"updated_at":"2026-11-02T18:20:39.851172Z"}],"ghsa":[{"id":"GHSA-68xw-r643-9p5w","title":"OpenClaw: Skill-command dispatch could skip before-tool-call hooks","description":"### Summary\n\nSkill-command dispatch could skip before-tool-call hooks. In affected versions, a skill command routed through the affected dispatch path could run without the same `runBeforeToolCallHook` coverage as other tool entry points.\n\nThis advisory is scoped to the named feature and configuration. It does not change OpenClaw's trusted-operator model: authenticated Gateway operators, installed plugins, and intentional local execution surfaces remain trusted unless a separate policy, approval, allowlist, sandbox, or auth boundary is crossed.\n\n### Impact\n\nWhen the affected feature is enabled and reachable, this could miss hook-based auditing or policy parity for that command path. Practical impact depends on the operator's configuration and whether lower-trust input can reach that path.\n\n### Patched Versions\n\nThe first stable patched version is `2026.5.6`.\n\n### Mitigations\n\navoid relying on hook-only enforcement for skill commands until patched. As general hardening, keep channel and tool allowlists narrow, avoid sharing one Gateway between mutually untrusted users, and disable the affected feature when it is not needed.","status":"published","published":"2026-06-18T20:16:30Z","modified":"2026-06-18T20:16:30Z","cvss":[{"version":"4.0","score":2.3,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N","level":"low"},{"version":"3.1","score":4.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N","level":"medium"}],"cwes":["CWE-693"],"updated_at":"2026-11-02T14:40:29.43528Z"},{"id":"GHSA-r7vv-6763-m739","title":"Duplicate Advisory: Skill-command dispatch could skip before-tool-call hooks","description":"## Duplicate Advisory\n\nThis advisory has been withdrawn because it is a duplicate of GHSA-68xw-r643-9p5w. This link is maintained to preserve external references.\n\n## Original Description\nOpenClaw before 2026.5.6 contains a hook bypass vulnerability where skill commands routed through the affected dispatch path skip before-tool-call hook coverage. Attackers can exploit this by sending skill commands through the vulnerable dispatch path to bypass hook-based auditing and policy enforcement mechanisms.","status":"withdrawn","published":"2026-06-16T21:31:58Z","modified":"2026-06-18T20:15:50Z","cvss":[{"version":"4.0","score":2.3,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N","level":"low"},{"version":"3.1","score":4.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N","level":"medium"}],"cwes":["CWE-693"],"updated_at":"2026-11-02T14:40:29.43528Z"}],"nvd":[{"id":"CVE-2026-53845","description":"OpenClaw before 2026.5.6 contains a hook bypass vulnerability where skill commands routed through the affected dispatch path skip before-tool-call hook coverage. Attackers can exploit this by sending skill commands through the vulnerable dispatch path to bypass hook-based auditing and policy enforcement mechanisms.","status":"published","published":"2026-06-16T19:17:01.52Z","modified":"2026-06-17T20:30:25.143Z","cvss":[{"version":"4.0","score":2.3,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","level":"low","assessor":"secondary"},{"version":"3.1","score":4.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N","level":"medium","assessor":"secondary"}],"cwes":["CWE-693"],"updated_at":"2026-11-02T14:12:24.19758Z"}],"osv":[{"id":"CVE-2026-53845","title":"OpenClaw \u003c 2026.5.6 - Skill-Command Dispatch Hook Bypass via Before-Tool-Call Hook Skipping","description":"OpenClaw before 2026.5.6 contains a hook bypass vulnerability where skill commands routed through the affected dispatch path skip before-tool-call hook coverage. Attackers can exploit this by sending skill commands through the vulnerable dispatch path to bypass hook-based auditing and policy enforcement mechanisms.","status":"published","published":"2026-06-16T18:04:56.803Z","modified":"2026-10-28T02:31:06.367526977Z","cvss":[{"version":"4.0","score":2.3,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N","level":"low"}],"cwes":["CWE-693"],"updated_at":"2026-11-02T15:45:08.132336Z"},{"id":"GHSA-68xw-r643-9p5w","title":"OpenClaw: Skill-command dispatch could skip before-tool-call hooks","description":"### Summary\n\nSkill-command dispatch could skip before-tool-call hooks. In affected versions, a skill command routed through the affected dispatch path could run without the same `runBeforeToolCallHook` coverage as other tool entry points.\n\nThis advisory is scoped to the named feature and configuration. It does not change OpenClaw's trusted-operator model: authenticated Gateway operators, installed plugins, and intentional local execution surfaces remain trusted unless a separate policy, approval, allowlist, sandbox, or auth boundary is crossed.\n\n### Impact\n\nWhen the affected feature is enabled and reachable, this could miss hook-based auditing or policy parity for that command path. Practical impact depends on the operator's configuration and whether lower-trust input can reach that path.\n\n### Patched Versions\n\nThe first stable patched version is `2026.5.6`.\n\n### Mitigations\n\navoid relying on hook-only enforcement for skill commands until patched. As general hardening, keep channel and tool allowlists narrow, avoid sharing one Gateway between mutually untrusted users, and disable the affected feature when it is not needed.","status":"published","published":"2026-06-18T20:16:30Z","modified":"2026-06-18T20:41:28.386486Z","cvss":[{"version":"3.1","score":4.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N","level":"medium"},{"version":"4.0","score":2.3,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N","level":"low"}],"cwes":["CWE-693"],"updated_at":"2026-11-02T15:46:39.618611Z"},{"id":"GHSA-r7vv-6763-m739","title":"Duplicate Advisory: Skill-command dispatch could skip before-tool-call hooks","description":"## Duplicate Advisory\n\nThis advisory has been withdrawn because it is a duplicate of GHSA-68xw-r643-9p5w. This link is maintained to preserve external references.\n\n## Original Description\nOpenClaw before 2026.5.6 contains a hook bypass vulnerability where skill commands routed through the affected dispatch path skip before-tool-call hook coverage. Attackers can exploit this by sending skill commands through the vulnerable dispatch path to bypass hook-based auditing and policy enforcement mechanisms.","status":"withdrawn","published":"2026-06-16T21:31:58Z","modified":"2026-06-18T20:30:23.882539273Z","cvss":[{"version":"3.1","score":4.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N","level":"medium"},{"version":"4.0","score":2.3,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N","level":"low"}],"cwes":["CWE-693"],"updated_at":"2026-11-02T15:46:55.480549Z"}]}}