{"id":"GHSA-9f72-qcpw-2hxc","aliases":[],"status":"published","title":"OpenClaw: Native prompt image auto-load did not honor tools.fs.workspaceOnly in sandboxed runs","description":"### Summary\nIn sandboxed runs, native prompt image auto-load did not honor `tools.fs.workspaceOnly=true`.\n\nThis optional hardening setting is **not enabled by default**. When operators enabled it, prompt text could still reference mounted out-of-workspace image paths (for example `/agent/secret.png`) and load those image bytes for vision-capable model input.\n\n### Affected Packages / Versions\n- Package: `openclaw` (npm)\n- Latest published npm version at triage time: `2026.2.23`\n- Vulnerable version range: `\u003c= 2026.2.23`\n- Patched version (planned next release): `2026.2.24`\n\n### Conditions Required\nThis issue required all of the following:\n- sandbox mode enabled,\n- `tools.fs.workspaceOnly=true` configured,\n- an out-of-workspace mount path reachable from the sandbox (for example `/agent`),\n- vision-capable model path active for native prompt image loading.\n\n### Technical Details\nNative prompt image ingestion (`detectAndLoadPromptImages` / `loadImageFromRef`) resolved and read sandbox paths but did not apply the same workspace-root assertion used by file tools when `tools.fs.workspaceOnly` was set.\n\n### Fix Commit(s)\n- `370d115549c0dadace0902775eea0d5094aedfdc`\n\n### Verification\n- `pnpm check`\n- `pnpm exec vitest run --config vitest.gateway.config.ts`\n- `pnpm test:fast`\n\n### Release Process Note\n`patched_versions` is pre-set to the planned next release (`2026.2.24`) so once npm release is available, this advisory only needs publish action.\n\nOpenClaw thanks @tdjackey for reporting.\n\n\n### Publication Update (2026-02-25)\n`openclaw@2026.2.24` is published on npm and contains the fix commit(s) listed above. This advisory now marks `\u003e= 2026.2.24` as patched.","severity":{"version":"4.0","score":8.9,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:N/VA:N/SC:H/SI:N/SA:N","level":"high","from":"ghsa"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-200","CWE-284"],"published":"2026-03-03T19:08:08Z","modified":"2026-03-04T15:14:41Z","fixes":[{"ecosystem":"npm","package":"openclaw","fixed_in":["2026.2.24"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"npm","package":"openclaw","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"2026.2.23"},{"fixed":"2026.2.24"}]}]},{"source":"osv","ecosystem":"npm","package":"openclaw","ranges":[{"type":"SEMVER","events":[{"introduced":"0"},{"fixed":"2026.2.24"}]}]}],"references":[{"url":"https://github.com/openclaw/openclaw/security/advisories/GHSA-9f72-qcpw-2hxc","tags":["web"]},{"url":"https://github.com/openclaw/openclaw/commit/370d115549c0dadace0902775eea0d5094aedfdc","tags":["web"]},{"url":"https://github.com/advisories/GHSA-9f72-qcpw-2hxc"},{"url":"https://github.com/openclaw/openclaw","tags":["package"]}],"sources":{"ghsa":[{"id":"GHSA-9f72-qcpw-2hxc","title":"OpenClaw: Native prompt image auto-load did not honor tools.fs.workspaceOnly in sandboxed runs","description":"### Summary\nIn sandboxed runs, native prompt image auto-load did not honor `tools.fs.workspaceOnly=true`.\n\nThis optional hardening setting is **not enabled by default**. When operators enabled it, prompt text could still reference mounted out-of-workspace image paths (for example `/agent/secret.png`) and load those image bytes for vision-capable model input.\n\n### Affected Packages / Versions\n- Package: `openclaw` (npm)\n- Latest published npm version at triage time: `2026.2.23`\n- Vulnerable version range: `\u003c= 2026.2.23`\n- Patched version (planned next release): `2026.2.24`\n\n### Conditions Required\nThis issue required all of the following:\n- sandbox mode enabled,\n- `tools.fs.workspaceOnly=true` configured,\n- an out-of-workspace mount path reachable from the sandbox (for example `/agent`),\n- vision-capable model path active for native prompt image loading.\n\n### Technical Details\nNative prompt image ingestion (`detectAndLoadPromptImages` / `loadImageFromRef`) resolved and read sandbox paths but did not apply the same workspace-root assertion used by file tools when `tools.fs.workspaceOnly` was set.\n\n### Fix Commit(s)\n- `370d115549c0dadace0902775eea0d5094aedfdc`\n\n### Verification\n- `pnpm check`\n- `pnpm exec vitest run --config vitest.gateway.config.ts`\n- `pnpm test:fast`\n\n### Release Process Note\n`patched_versions` is pre-set to the planned next release (`2026.2.24`) so once npm release is available, this advisory only needs publish action.\n\nOpenClaw thanks @tdjackey for reporting.\n\n\n### Publication Update (2026-02-25)\n`openclaw@2026.2.24` is published on npm and contains the fix commit(s) listed above. This advisory now marks `\u003e= 2026.2.24` as patched.","status":"published","published":"2026-03-03T19:08:08Z","modified":"2026-03-03T19:08:10Z","cvss":[{"version":"4.0","score":8.9,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:N/VA:N/SC:H/SI:N/SA:N","level":"high"}],"cwes":["CWE-200","CWE-284"],"updated_at":"2026-11-02T14:39:30.031684Z"}],"osv":[{"id":"GHSA-9f72-qcpw-2hxc","title":"OpenClaw: Native prompt image auto-load did not honor tools.fs.workspaceOnly in sandboxed runs","description":"### Summary\nIn sandboxed runs, native prompt image auto-load did not honor `tools.fs.workspaceOnly=true`.\n\nThis optional hardening setting is **not enabled by default**. When operators enabled it, prompt text could still reference mounted out-of-workspace image paths (for example `/agent/secret.png`) and load those image bytes for vision-capable model input.\n\n### Affected Packages / Versions\n- Package: `openclaw` (npm)\n- Latest published npm version at triage time: `2026.2.23`\n- Vulnerable version range: `\u003c= 2026.2.23`\n- Patched version (planned next release): `2026.2.24`\n\n### Conditions Required\nThis issue required all of the following:\n- sandbox mode enabled,\n- `tools.fs.workspaceOnly=true` configured,\n- an out-of-workspace mount path reachable from the sandbox (for example `/agent`),\n- vision-capable model path active for native prompt image loading.\n\n### Technical Details\nNative prompt image ingestion (`detectAndLoadPromptImages` / `loadImageFromRef`) resolved and read sandbox paths but did not apply the same workspace-root assertion used by file tools when `tools.fs.workspaceOnly` was set.\n\n### Fix Commit(s)\n- `370d115549c0dadace0902775eea0d5094aedfdc`\n\n### Verification\n- `pnpm check`\n- `pnpm exec vitest run --config vitest.gateway.config.ts`\n- `pnpm test:fast`\n\n### Release Process Note\n`patched_versions` is pre-set to the planned next release (`2026.2.24`) so once npm release is available, this advisory only needs publish action.\n\nOpenClaw thanks @tdjackey for reporting.\n\n\n### Publication Update (2026-02-25)\n`openclaw@2026.2.24` is published on npm and contains the fix commit(s) listed above. This advisory now marks `\u003e= 2026.2.24` as patched.","status":"published","published":"2026-03-03T19:08:08Z","modified":"2026-03-04T15:14:41.045535Z","cvss":[{"version":"4.0","score":8.9,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:N/VA:N/SC:H/SI:N/SA:N","level":"high"}],"cwes":["CWE-200","CWE-284"],"updated_at":"2026-11-02T15:46:43.524801Z"}]}}