fix(make-pdf): replace regex sanitizer with parser-backed sanitization

Signed-off-by: Arpit Jain <arpitjain099@gmail.com>
This commit is contained in:
Arpit Jain 2026-05-12 08:35:13 +00:00 committed by arpitjain099
parent 9fd03fae9e
commit 875e6ab077
No known key found for this signature in database
4 changed files with 78 additions and 67 deletions

View File

@ -12,6 +12,7 @@
"marked": "^18.0.2",
"playwright": "^1.58.2",
"puppeteer-core": "^24.40.0",
"sanitize-html": "^2.17.3",
"socks": "^2.8.8",
},
"devDependencies": {
@ -243,8 +244,12 @@
"data-uri-to-buffer": ["data-uri-to-buffer@6.0.2", "", {}, "sha512-7hvf7/GW8e86rW0ptuwS3OcBGDjIi6SZva7hCyWC0yYry2cOPmLIjXAUHI6DK2HsnwJd9ifmt57i8eV2n4YNpw=="],
"dayjs": ["dayjs@1.11.21", "", {}, "sha512-98IT+HOahAisibz/yjKbzuOBwYcjJ7BCLPzARyHiyEBmRz4fatF+KPJszEHXsGYjUG234aH/cOjW1wwTbKUZlA=="],
"debug": ["debug@4.4.3", "", { "dependencies": { "ms": "^2.1.3" } }, "sha512-RGwwWnwQvkVfavKVt22FGLw+xYSdzARwm0ru6DhTVA3umU5hZc28V3kO4stgYryrTlLpuvgI9GiijltAjNbcqA=="],
"deepmerge": ["deepmerge@4.3.1", "", {}, "sha512-3sUqbMEc77XqpdNO7FRyRog+eW3ph+GYCbj+rK+uYyRMuwsVy0rMiVtPn+QJlKFvWP/1PYpapqYn0Me2knFn+A=="],
"define-data-property": ["define-data-property@1.1.4", "", { "dependencies": { "es-define-property": "^1.0.0", "es-errors": "^1.3.0", "gopd": "^1.0.1" } }, "sha512-rBMvIzlpA8v6E+SJZoo++HAYqsLrkg7MSfIinMPFhmkorw7X+dOXVJQs+QT69zGkzMyfDnIMN2Wid1+NbL3T+A=="],
"define-properties": ["define-properties@1.2.1", "", { "dependencies": { "define-data-property": "^1.0.1", "has-property-descriptors": "^1.0.0", "object-keys": "^1.1.1" } }, "sha512-8QmQKqEASLd5nx0U1B1okLElbUuuttJ/AnYmRXbbbGDWh6uS208EjD4Xqq/I9wK7u0v6O08XhTWnt5XtEbR6Dg=="],
@ -261,15 +266,15 @@
"diff": ["diff@7.0.0", "", {}, "sha512-PJWHUb1RFevKCwaFA9RlG5tCd+FO5iRh9A8HEtkmBH2Li03iJriB6m6JIN4rGz3K3JLawI7/veA1xzRKP6ISBw=="],
"dom-serializer": ["dom-serializer@0.2.2", "", { "dependencies": { "domelementtype": "^2.0.1", "entities": "^2.0.0" } }, "sha512-2/xPb3ORsQ42nHYiSunXkDjPLBaEj/xTwUO4B7XCZQTRk7EBtTOPaygh10YAAh2OI1Qrp6NWfpAhzswj0ydt9g=="],
"dom-serializer": ["dom-serializer@2.0.0", "", { "dependencies": { "domelementtype": "^2.3.0", "domhandler": "^5.0.2", "entities": "^4.2.0" } }, "sha512-wIkAryiqt/nV5EQKqQpo3SToSOV9J0DnbJqwK7Wv/Trc92zIAYZ4FlMu+JPFW1DfGFt81ZTCGgDEabffXeLyJg=="],
"dom-walk": ["dom-walk@0.1.2", "", {}, "sha512-6QvTW9mrGeIegrFXdtQi9pk7O/nSK6lSdXW2eqUspN5LWD7UTji2Fqw5V2YLjBpHEoU9Xl/eUWNpDeZvoyOv2w=="],
"domelementtype": ["domelementtype@1.3.1", "", {}, "sha512-BSKB+TSpMpFI/HOxCNr1O8aMOTZ8hT3pM3GQ0w/mWRmkhEDSFJkkyzz4XQsBV44BChwGkrDfMyjVD0eA2aFV3w=="],
"domelementtype": ["domelementtype@2.3.0", "", {}, "sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw=="],
"domhandler": ["domhandler@2.4.2", "", { "dependencies": { "domelementtype": "1" } }, "sha512-JiK04h0Ht5u/80fdLMCEmV4zkNh2BcoMFBmZ/91WtYZ8qVXSKjiw7fXMgFPnHcSZgOo3XdinHvmnDUeMf5R4wA=="],
"domhandler": ["domhandler@5.0.3", "", { "dependencies": { "domelementtype": "^2.3.0" } }, "sha512-cgwlv/1iFQiFnU96XXgROh8xTeetsnJiDsTc7TYCLFd9+/WNkIqPTxiM/8pSd8VIrhXGTf1Ny1q1hquVqDJB5w=="],
"domutils": ["domutils@1.7.0", "", { "dependencies": { "dom-serializer": "0", "domelementtype": "1" } }, "sha512-Lgd2XcJ/NjEw+7tFvfKxOzCYKZsdct5lczQ2ZaQY8Djz7pfAD3Gbp8ySJWtreII/vDlMVmxwa6pHmdxIYgttDg=="],
"domutils": ["domutils@3.2.2", "", { "dependencies": { "dom-serializer": "^2.0.0", "domelementtype": "^2.3.0", "domhandler": "^5.0.3" } }, "sha512-6kZKyUajlDuqlHKVX1w7gyslj9MPIXzIFiz/rGu35uC1wMi+kMhQwGhl4lt9unC9Vb9INnY9Z3/ZA3+FhASLaw=="],
"dunder-proto": ["dunder-proto@1.0.1", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.1", "es-errors": "^1.3.0", "gopd": "^1.2.0" } }, "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A=="],
@ -283,7 +288,7 @@
"ent": ["ent@2.2.2", "", { "dependencies": { "call-bound": "^1.0.3", "es-errors": "^1.3.0", "punycode": "^1.4.1", "safe-regex-test": "^1.1.0" } }, "sha512-kKvD1tO6BM+oK9HzCPpUdRb4vKFQY/FPTFmurMvh6LlN68VMrdj77w8yp51/kDbpkFOS9J8w5W6zIzgM2H8/hw=="],
"entities": ["entities@1.1.2", "", {}, "sha512-f2LZMYl1Fzu7YSBKg+RoROelpOaNrcGmE9AZubeDfrCEia483oW4MI4VyFd5VNHIgQ/7qm1I0wUHK1eJnn2y2w=="],
"entities": ["entities@7.0.1", "", {}, "sha512-TWrgLOFUQTH994YUyl1yT4uyavY5nNB5muff+RtWaqNVCAK408b5ZnnbNAUEWLTCpum9w6arT70i1XdQ4UeOPA=="],
"error": ["error@4.4.0", "", { "dependencies": { "camelize": "^1.0.0", "string-template": "~0.2.0", "xtend": "~4.0.0" } }, "sha512-SNDKualLUtT4StGFP7xNfuFybL2f6iJujFtrWuvJqGbVQGaN+adE23veqzPz1hjUjTunLi2EnJ+0SJxtbJreKw=="],
@ -381,7 +386,7 @@
"html-to-vdom": ["html-to-vdom@0.7.0", "", { "dependencies": { "ent": "^2.0.0", "htmlparser2": "^3.8.2" } }, "sha512-k+d2qNkbx0JO00KezQsNcn6k2I/xSBP4yXYFLvXbcasTTDh+RDLUJS3puxqyNnpdyXWRHFGoKU7cRmby8/APcQ=="],
"htmlparser2": ["htmlparser2@3.10.1", "", { "dependencies": { "domelementtype": "^1.3.1", "domhandler": "^2.3.0", "domutils": "^1.5.1", "entities": "^1.1.1", "inherits": "^2.0.1", "readable-stream": "^3.1.1" } }, "sha512-IgieNijUMbkDovyoKObU1DUhm1iwNYE/fuifEoEHfd1oZKZDaONBSkal7Y01shxsM49R4XaMdGez3WnF9UfiCQ=="],
"htmlparser2": ["htmlparser2@10.1.0", "", { "dependencies": { "domelementtype": "^2.3.0", "domhandler": "^5.0.3", "domutils": "^3.2.2", "entities": "^7.0.1" } }, "sha512-VTZkM9GWRAtEpveh7MSF6SjjrpNVNNVJfFup7xTY3UpFtm67foy9HDVXneLtFVt4pMz5kZtgNcvCniNFb1hlEQ=="],
"http-errors": ["http-errors@2.0.1", "", { "dependencies": { "depd": "~2.0.0", "inherits": "~2.0.4", "setprototypeof": "~1.2.0", "statuses": "~2.0.2", "toidentifier": "~1.0.1" } }, "sha512-4FbRdAX+bSdmo4AUFuS0WNiPz8NgFt+r8ThgNWmlrjQjt1Q7ZR9+zTlce2859x4KSXrwIsaeTqDoKQmtP8pLmQ=="],
@ -409,6 +414,8 @@
"is-object": ["is-object@1.0.2", "", {}, "sha512-2rRIahhZr2UWb45fIOuvZGpFtz0TyOZLf32KxBbSoUCeZR495zCKlWUKKUByk3geS2eAs7ZAABt0Y/Rx0GiQGA=="],
"is-plain-object": ["is-plain-object@5.0.0", "", {}, "sha512-VRSzKkbMm5jMDoKLbltAkFQ5Qr7VDiTFGXxYFXXowVj387GeGNOCsOH6Msy00SGZ3Fp84b1Naa1psqgcCIEP5Q=="],
"is-promise": ["is-promise@4.0.0", "", {}, "sha512-hvpoI6korhJMnej285dSg6nu1+e6uxs7zG3BYAm5byqDsgJNWwxzM6z6iZiAgQR4TJ30JmBTOwqZUw3WlyH3AQ=="],
"is-regex": ["is-regex@1.2.1", "", { "dependencies": { "call-bound": "^1.0.2", "gopd": "^1.2.0", "has-tostringtag": "^1.0.2", "hasown": "^2.0.2" } }, "sha512-MjYsKHO5O7mCsmRGxWcLWheFqN9DJ/2TmngvjKXihe6efViPqc274+Fx/4fYj/r03+ESvBdTXK0V6tA3rgez1g=="],
@ -429,6 +436,8 @@
"jszip": ["jszip@3.10.1", "", { "dependencies": { "lie": "~3.3.0", "pako": "~1.0.2", "readable-stream": "~2.3.6", "setimmediate": "^1.0.5" } }, "sha512-xXDvecyTpGLrqFrvkrUSoxxfJI5AH7U8zxxtVclpsUtMCq4JQ290LY8AW5c7Ggnr/Y/oK+bQMbqK2qmtk3pN4g=="],
"launder": ["launder@1.7.1", "", { "dependencies": { "dayjs": "^1.11.7" } }, "sha512-mU6WRz5EusL9ZZuiZ5SO4Y6C0P9PAUR9iwdb6bzj4KDihm28DiHFw+/yk9DBH4f+Pv1wuzQ4e2jV3oQ7mkIqvw=="],
"lie": ["lie@3.3.0", "", { "dependencies": { "immediate": "~3.0.5" } }, "sha512-UaiMJzeWRlEujzAuw5LokY1L5ecNQYZKfmyZ9L7wDHb/p5etKaxXhohBcrw0EYby+G/NA52vRSN4N39dxHAIwQ=="],
"lodash": ["lodash@4.18.1", "", {}, "sha512-dMInicTPVE8d1e5otfwmmjlxkZoUpiVLwyeTdUsi/Caj/gfzzblBcCE5sRHV/AsjuCmxWrte2TNGSYuCeCq+0Q=="],
@ -489,6 +498,8 @@
"pako": ["pako@1.0.11", "", {}, "sha512-4hLB8Py4zZce5s4yd9XzopqwVv/yGNhV1Bl8NTmCq1763HeK2+EwVTv+leGeL13Dnh2wfbqowVPXCIO0z4taYw=="],
"parse-srcset": ["parse-srcset@1.0.2", "", {}, "sha512-/2qh0lav6CmI15FzA3i/2Bzk2zCgQhGMkvhOhKNcBVQ1ldgpbfiNTVslmooUmWJcADi1f1kIeynbDRVzNlfR6Q=="],
"parseurl": ["parseurl@1.3.3", "", {}, "sha512-CiyeOxFT/JZyN5m0z9PfXw4SCBJ6Sygz1Dpl0wqjlhDEGGBP1GnsUVEL0p63hoG1fcj3fHynXi9NYO4nWOL+qQ=="],
"path-key": ["path-key@3.1.1", "", {}, "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q=="],
@ -497,6 +508,8 @@
"pend": ["pend@1.2.0", "", {}, "sha512-F3asv42UuXchdzt+xXqfW1OGlVBe+mxa2mqI0pg5yAHZPvFmY3Y6drSf/GQ1A86WgWEN9Kzh/WrgKa6iGcHXLg=="],
"picocolors": ["picocolors@1.1.1", "", {}, "sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA=="],
"pkce-challenge": ["pkce-challenge@5.0.1", "", {}, "sha512-wQ0b/W4Fr01qtpHlqSqspcj3EhBvimsdh0KlHhH8HRZnMsEa0ea2fTULOXOS9ccQr3om+GcGRk4e+isrZWV8qQ=="],
"platform": ["platform@1.3.6", "", {}, "sha512-fnWVljUchTro6RiCFvCXBbNhJc2NijN7oIQxbwsyL0buWJPG85v81ehlHI9fXrJsMNgTofEoWIQeClKpgxFLrg=="],
@ -505,6 +518,8 @@
"playwright-core": ["playwright-core@1.58.2", "", { "bin": { "playwright-core": "cli.js" } }, "sha512-yZkEtftgwS8CsfYo7nm0KE8jsvm6i/PTgVtB8DL726wNf6H2IMsDuxCpJj59KDaxCtSnrWan2AeDqM7JBaultg=="],
"postcss": ["postcss@8.5.15", "", { "dependencies": { "nanoid": "^3.3.12", "picocolors": "^1.1.1", "source-map-js": "^1.2.1" } }, "sha512-FfR8sjd4em2T6fb3I2MwAJU7HWVMr9zba+enmQeeWFfCbm+UOC/0X4DS8XtpUTMwWMGbjKYP7xjfNekzyGmB3A=="],
"process": ["process@0.11.10", "", {}, "sha512-cdGef/drWFoydD1JsMzuFf8100nZl+GT+yacc2bEced5f9Rjk4z+WtFUTBu9PhOi9j/jfmBPu0mMEY4wIdAF8A=="],
"process-nextick-args": ["process-nextick-args@2.0.1", "", {}, "sha512-3ouUOpQhtgrbOa17J7+uxOTpITYWaGP7/AhoR3+A+/1e9skrzelGi/dXzEYyvbxubEF6Wn2ypscTKiKJFFn1ag=="],
@ -549,6 +564,8 @@
"safer-buffer": ["safer-buffer@2.1.2", "", {}, "sha512-YZo3K82SD7Riyi0E1EQPojLz7kpepnSQI9IyPbHHg1XXXevb5dJI7tpyN2ADxGcQbHG7vcyRHk0cbwqcQriUtg=="],
"sanitize-html": ["sanitize-html@2.17.5", "", { "dependencies": { "deepmerge": "^4.2.2", "escape-string-regexp": "^4.0.0", "htmlparser2": "^10.1.0", "is-plain-object": "^5.0.0", "launder": "^1.7.1", "parse-srcset": "^1.0.2", "postcss": "^8.3.11" } }, "sha512-ZmU1joGRrvoyctKIiuwUxqR6moLoU2Wk+2bMccN6f7UwhAmwYDvWziqPxRDDN2Qip62NqnIrVrT9akbL6Wretg=="],
"semver": ["semver@7.7.4", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-vFKC2IEtQnVhpT78h1Yp8wzwrf8CM+MzKMHGJZfBtzhZNycRFnXsHk6E5TxIkkMsgNS7mdX3AGB7x2QM2di4lA=="],
"semver-compare": ["semver-compare@1.0.0", "", {}, "sha512-YM3/ITh2MJ5MtzaM429anh+x2jiLVjqILF4m4oyQB18W7Ggea7BfqdH/wGMK7dDiMghv/6WG7znWMwUDzJiXow=="],
@ -585,6 +602,8 @@
"source-map": ["source-map@0.6.1", "", {}, "sha512-UjgapumWlbMhkBgzT7Ykc5YXUT46F0iKu8SGXq0bcwP5dz/h0Plj6enJqjz1Zbq2l5WaqYnrVbwWOWMyF3F47g=="],
"source-map-js": ["source-map-js@1.2.1", "", {}, "sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA=="],
"sprintf-js": ["sprintf-js@1.1.3", "", {}, "sha512-Oo+0REFV59/rz3gfJNKQiBlwfHaSESl1pcGyABQsnnIfWOFt6JNj5gCog2U6MLZ//IGYD+nA8nI+mTShREReaA=="],
"statuses": ["statuses@2.0.2", "", {}, "sha512-DvEy55V3DB7uknRo+4iOGT5fP1slR8wQohVdknigZPMpMstaKJQWhwiYBACJE3Ul2pTnATihhBYnRhZQHGBiRw=="],
@ -679,15 +698,13 @@
"accepts/mime-types": ["mime-types@3.0.2", "", { "dependencies": { "mime-db": "^1.54.0" } }, "sha512-Lbgzdk0h4juoQ9fCKXW4by0UJqj+nOOrI9MJ1sSj4nI8aI2eo1qmvQEie4VD1glsS250n15LsWsYtCugiStS5A=="],
"dom-serializer/domelementtype": ["domelementtype@2.3.0", "", {}, "sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw=="],
"dom-serializer/entities": ["entities@2.2.0", "", {}, "sha512-p92if5Nz619I0w+akJrLZH0MX0Pb5DX39XOwQTtXSdQQOaYH03S1uIQp4mhOZtAXrxq4ViO67YTiLBo2638o9A=="],
"dom-serializer/entities": ["entities@4.5.0", "", {}, "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw=="],
"express/mime-types": ["mime-types@3.0.2", "", { "dependencies": { "mime-db": "^1.54.0" } }, "sha512-Lbgzdk0h4juoQ9fCKXW4by0UJqj+nOOrI9MJ1sSj4nI8aI2eo1qmvQEie4VD1glsS250n15LsWsYtCugiStS5A=="],
"express-rate-limit/ip-address": ["ip-address@10.1.0", "", {}, "sha512-XXADHxXmvT9+CRxhXg56LJovE+bmWnEWB78LB83VZTprKTmaC5QfruXocxzTZ2Kl0DNwKuBdlIhjL8LeY8Sf8Q=="],
"htmlparser2/readable-stream": ["readable-stream@3.6.2", "", { "dependencies": { "inherits": "^2.0.3", "string_decoder": "^1.1.1", "util-deprecate": "^1.0.1" } }, "sha512-9u/sniCrY3D5WdsERHzHE4G2YCXqoG5FTHUiCC4SIbr6XcLZBY05ya9EKjYek9O5xOAwjGq+1JdGBAS7Q9ScoA=="],
"html-to-vdom/htmlparser2": ["htmlparser2@3.10.1", "", { "dependencies": { "domelementtype": "^1.3.1", "domhandler": "^2.3.0", "domutils": "^1.5.1", "entities": "^1.1.1", "inherits": "^2.0.1", "readable-stream": "^3.1.1" } }, "sha512-IgieNijUMbkDovyoKObU1DUhm1iwNYE/fuifEoEHfd1oZKZDaONBSkal7Y01shxsM49R4XaMdGez3WnF9UfiCQ=="],
"onnxruntime-web/onnxruntime-common": ["onnxruntime-common@1.24.0-dev.20251116-b39e144322", "", {}, "sha512-BOoomdHYmNRL5r4iQ4bMvsl2t0/hzVQ3OM3PHD0gxeXu1PmggqBv3puZicEUVOA3AtHHYmqZtjMj9FOfGrATTw=="],
@ -707,6 +724,16 @@
"express/mime-types/mime-db": ["mime-db@1.54.0", "", {}, "sha512-aU5EJuIN2WDemCcAp2vFBfp/m4EAhWJnUNSSw0ixs7/kXbd6Pg64EmwJkNdFhB8aWt1sH2CTXrLxo/iAGV3oPQ=="],
"html-to-vdom/htmlparser2/domelementtype": ["domelementtype@1.3.1", "", {}, "sha512-BSKB+TSpMpFI/HOxCNr1O8aMOTZ8hT3pM3GQ0w/mWRmkhEDSFJkkyzz4XQsBV44BChwGkrDfMyjVD0eA2aFV3w=="],
"html-to-vdom/htmlparser2/domhandler": ["domhandler@2.4.2", "", { "dependencies": { "domelementtype": "1" } }, "sha512-JiK04h0Ht5u/80fdLMCEmV4zkNh2BcoMFBmZ/91WtYZ8qVXSKjiw7fXMgFPnHcSZgOo3XdinHvmnDUeMf5R4wA=="],
"html-to-vdom/htmlparser2/domutils": ["domutils@1.7.0", "", { "dependencies": { "dom-serializer": "0", "domelementtype": "1" } }, "sha512-Lgd2XcJ/NjEw+7tFvfKxOzCYKZsdct5lczQ2ZaQY8Djz7pfAD3Gbp8ySJWtreII/vDlMVmxwa6pHmdxIYgttDg=="],
"html-to-vdom/htmlparser2/entities": ["entities@1.1.2", "", {}, "sha512-f2LZMYl1Fzu7YSBKg+RoROelpOaNrcGmE9AZubeDfrCEia483oW4MI4VyFd5VNHIgQ/7qm1I0wUHK1eJnn2y2w=="],
"html-to-vdom/htmlparser2/readable-stream": ["readable-stream@3.6.2", "", { "dependencies": { "inherits": "^2.0.3", "string_decoder": "^1.1.1", "util-deprecate": "^1.0.1" } }, "sha512-9u/sniCrY3D5WdsERHzHE4G2YCXqoG5FTHUiCC4SIbr6XcLZBY05ya9EKjYek9O5xOAwjGq+1JdGBAS7Q9ScoA=="],
"send/mime-types/mime-db": ["mime-db@1.54.0", "", {}, "sha512-aU5EJuIN2WDemCcAp2vFBfp/m4EAhWJnUNSSw0ixs7/kXbd6Pg64EmwJkNdFhB8aWt1sH2CTXrLxo/iAGV3oPQ=="],
"socks-proxy-agent/socks/ip-address": ["ip-address@10.1.0", "", {}, "sha512-XXADHxXmvT9+CRxhXg56LJovE+bmWnEWB78LB83VZTprKTmaC5QfruXocxzTZ2Kl0DNwKuBdlIhjL8LeY8Sf8Q=="],
@ -714,5 +741,11 @@
"type-is/mime-types/mime-db": ["mime-db@1.54.0", "", {}, "sha512-aU5EJuIN2WDemCcAp2vFBfp/m4EAhWJnUNSSw0ixs7/kXbd6Pg64EmwJkNdFhB8aWt1sH2CTXrLxo/iAGV3oPQ=="],
"xmlbuilder2/@oozcitak/dom/@oozcitak/util": ["@oozcitak/util@8.0.0", "", {}, "sha512-+9Hq6yuoq/3TRV/n/xcpydGBq2qN2/DEDMqNTG7rm95K6ZE2/YY/sPyx62+1n8QsE9O26e5M1URlXsk+AnN9Jw=="],
"html-to-vdom/htmlparser2/domutils/dom-serializer": ["dom-serializer@0.2.2", "", { "dependencies": { "domelementtype": "^2.0.1", "entities": "^2.0.0" } }, "sha512-2/xPb3ORsQ42nHYiSunXkDjPLBaEj/xTwUO4B7XCZQTRk7EBtTOPaygh10YAAh2OI1Qrp6NWfpAhzswj0ydt9g=="],
"html-to-vdom/htmlparser2/domutils/dom-serializer/domelementtype": ["domelementtype@2.3.0", "", {}, "sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw=="],
"html-to-vdom/htmlparser2/domutils/dom-serializer/entities": ["entities@2.2.0", "", {}, "sha512-p92if5Nz619I0w+akJrLZH0MX0Pb5DX39XOwQTtXSdQQOaYH03S1uIQp4mhOZtAXrxq4ViO67YTiLBo2638o9A=="],
}
}

View File

@ -12,6 +12,7 @@
*/
import { marked } from "marked";
import sanitizeHtml from "sanitize-html";
import { smartypants } from "./smartypants";
import { printCss, type PrintCssOptions } from "./print-css";
import { applyImageDirectives } from "./image-policy";
@ -194,60 +195,34 @@ function decodeTypographicEntities(html: string): string {
/**
* Strip dangerous HTML from markdown-produced output.
*
* We can't use DOMPurify (server-side; adds a jsdom dep). A conservative
* regex sanitizer is fine for this use case because:
* 1. marked produces structured HTML (never malformed)
* 2. we only need to strip a fixed blacklist of elements + attrs
* 3. the output goes through Chromium's parser again, which normalizes
*
* What's stripped:
* - <script>, <iframe>, <object>, <embed>, <link>, <meta>, <base>, <form>
* (and their content).
* - on* event handler attributes (onclick, ONCLICK, etc.).
* - href/src with javascript: scheme.
* - <svg> tags with <script> inside them.
* Use a parser-backed sanitizer instead of regex matching. Regex-based HTML
* filtering is brittle and can be bypassed by malformed-but-browser-accepted
* markup.
*/
const SANITIZE_OPTIONS: sanitizeHtml.IOptions = {
// Keep common markdown output tags only; drop active/embedding content.
allowedTags: [
...sanitizeHtml.defaults.allowedTags,
"img",
"h1", "h2", "h3", "h4", "h5", "h6",
"section", "figure", "figcaption",
"table", "thead", "tbody", "tr", "th", "td",
],
allowedAttributes: {
a: ["href", "name", "target", "rel", "title"],
img: ["src", "alt", "title", "width", "height"],
'*': ["id", "class", "lang", "dir", "align"],
},
allowedSchemes: ["http", "https", "mailto", "tel", "data"],
allowedSchemesByTag: {
img: ["http", "https", "data"],
},
allowProtocolRelative: false,
disallowedTagsMode: "discard",
};
export function sanitizeUntrustedHtml(html: string): string {
let s = html;
// Elements to remove entirely (including content).
const DANGER_TAGS = [
"script", "iframe", "object", "embed", "link", "meta", "base", "form",
"applet", "frame", "frameset",
];
for (const tag of DANGER_TAGS) {
const re = new RegExp(`<${tag}\\b[\\s\\S]*?</${tag}>`, "gi");
s = s.replace(re, "");
// Self-closing / unclosed variants
const selfRe = new RegExp(`<${tag}\\b[^>]*/?>`, "gi");
s = s.replace(selfRe, "");
}
// SVG <script>
s = s.replace(/<svg([^>]*)>([\s\S]*?)<\/svg>/gi, (_, attrs, body) => {
return `<svg${attrs}>${body.replace(/<script\b[\s\S]*?<\/script>/gi, "")}</svg>`;
});
// Event handler attributes (on* in any case).
s = s.replace(/\s+on[a-zA-Z]+\s*=\s*"[^"]*"/gi, "");
s = s.replace(/\s+on[a-zA-Z]+\s*=\s*'[^']*'/gi, "");
s = s.replace(/\s+on[a-zA-Z]+\s*=\s*[^\s>]+/gi, "");
// javascript: URLs in href/src/action/formaction
s = s.replace(
/(\s(?:href|src|action|formaction|xlink:href)\s*=\s*)(?:"javascript:[^"]*"|'javascript:[^']*'|javascript:[^\s>]+)/gi,
'$1"#"',
);
// srcdoc attribute (iframe escape hatch — already stripped via iframe above,
// but defense-in-depth).
s = s.replace(/\s+srcdoc\s*=\s*"[^"]*"/gi, "");
s = s.replace(/\s+srcdoc\s*=\s*'[^']*'/gi, "");
// style="url(javascript:..)" — strip javascript: inside style attrs.
s = s.replace(/url\(\s*javascript:[^)]*\)/gi, "url(#)");
return s;
return sanitizeHtml(html, SANITIZE_OPTIONS);
}
// ─── Cover / TOC / Chapter helpers ────────────────────────────────────
@ -416,7 +391,7 @@ function composeMargins(opts: {
}
function stripTags(html: string): string {
return html.replace(/<[^>]+>/g, "");
return sanitizeHtml(html, { allowedTags: [], allowedAttributes: {} });
}
export function escapeHtml(s: string): string {

View File

@ -101,18 +101,20 @@ describe("sanitizeUntrustedHtml", () => {
expect(sanitizeUntrustedHtml(input2)).not.toContain("ONCLICK");
});
test("rewrites javascript: URLs in href to #", () => {
test("removes javascript: URLs in href", () => {
const input = `<a href="javascript:alert(1)">bad</a>`;
const out = sanitizeUntrustedHtml(input);
expect(out).not.toContain("javascript:");
expect(out).toContain('href="#"');
expect(out).toContain("<a");
expect(out).not.toContain("href=");
});
test("strips inline SVG <script>", () => {
test("drops inline SVG content", () => {
const input = `<svg><script>alert(1)</script><circle r="5"/></svg>`;
const out = sanitizeUntrustedHtml(input);
expect(out).not.toContain("<script");
expect(out).toContain("<circle");
expect(out).not.toContain("<svg");
expect(out).not.toContain("<circle");
});
test("strips <object>, <embed>, <link>, <meta>, <base>, <form>", () => {

View File

@ -56,6 +56,7 @@
"marked": "^18.0.2",
"playwright": "^1.58.2",
"puppeteer-core": "^24.40.0",
"sanitize-html": "^2.17.3",
"socks": "^2.8.8"
},
"engines": {