From de5c2da0027dbc767148e830df19c16da624f407 Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Mon, 13 Jul 2026 03:47:20 +0000
Subject: [PATCH] fix(extractors): refine upload_security regexes to eliminate
 false positives\n\n- Fix KEY_FROM_NAME flagging benign originalname template
 strings.\n- Fix TRUST_CLIENT_MIME flagging safe usages like logging.\n- Fix
 ACCEPT_SVG flagging strict rejection cases.\n- Add permanent regression tests
 in `test_pentest_regressions.py`.

---
 CHANGELOG.md                                  |  4 ++++
 .../extractors/upload_security.py             | 15 ++++++++-----
 tests/test_pentest_regressions.py             | 22 +++++++++++++++++++
 3 files changed, 36 insertions(+), 5 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index db53af9..cdebd4e 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/).
 
 ## [Unreleased]
 
+### Fixed
+- **Upload Security Extractor False Positives** — refined `KEY_FROM_NAME`, `TRUST_CLIENT_MIME`, and `ACCEPT_SVG` regexes to stop flagging benign usage of originalname in string templates, common mimetype logging, and explicit SVG rejection conditions.
+
+
 ### Added
 
 - **No-Row-Level-Security detection** (`missing-rls` class, in `schemas.py` + the ledger) — committed
diff --git a/src/websec_validator/extractors/upload_security.py b/src/websec_validator/extractors/upload_security.py
index dc0c2ba..19edc30 100644
--- a/src/websec_validator/extractors/upload_security.py
+++ b/src/websec_validator/extractors/upload_security.py
@@ -25,11 +25,16 @@
 ALLOW_LIST = re.compile(r"isAllowedMediaType|allowedMimeTypes|allow[_-]?list|whitelist|ALLOWED_(?:MIME|TYPES|EXT)"
                         r"|ACCEPTED_(?:MIME|TYPES?|EXT)|accepted(?:Mime|File|Content)?(?:Types?|Extensions?)"
                         r"|\bfile-type\b|fileTypeFrom|magic[_-]?byte|detectContentType|\.fromBuffer\b|sniff", re.I)
-KEY_FROM_NAME = re.compile(r"(?:Key|key|path|filename|filepath|destination|filename\s*\()\s*[:=(][^;\n]{0,90}"
-                           r"\b(?:originalname|originalName|file\.name)\b"
-                           r"|`[^`]*\$\{[^}]*\boriginalname\b[^}]*\}[^`]*`", re.I)
-TRUST_CLIENT_MIME = re.compile(r"(?:req\.files?\.[\w$.]*\.|\bfile\.)mimetype\b|headers\[['\"]content-type['\"]\]", re.I)
-ACCEPT_SVG = re.compile(r"image/svg\+xml|['\"]svg['\"]", re.I)
+KEY_FROM_NAME = re.compile(r"(?:Key|key|path|filename|filepath|destination|filename\s*\()\s*[:=(]\s*"
+                           r"(?:[^;{\n]{0,90}?)?"
+                           r"(?:\b(?:originalname|originalName|file\.name)\b"
+                           r"|`[^`]*\$\{[^}]*\b(?:originalname|originalName|file\.name)\b[^}]*\}[^`]*`)", re.I)
+TRUST_CLIENT_MIME = re.compile(r"(?:===|!==|==|!=|\.includes\s*\(|[=:]\s*|switch\s*\(\s*|(?<!\blog)(?<!\binfo)(?<!\bwarn)(?<!\berror)(?<!\bdebug)\s*\(\s*[^);]*?)(?:req\.files?\.[\w$.]*\.|\bfile\.)mimetype\b"
+                               r"|(?:req\.files?\.[\w$.]*\.|\bfile\.)mimetype\b\s*(?:===|!==|==|!=)"
+                               r"|headers\[['\"]content-type['\"]\]\s*(?:===|!==|==|!=)", re.I)
+ACCEPT_SVG = re.compile(r"\[[^\]]*(?:image/svg\+xml|['\"]svg['\"])[^\]]*\]"
+                        r"|(?:\bincludes\b|\bindexOf\b)\s*\(\s*(?:['\"]image/svg\+xml['\"]|['\"]svg['\"])\s*\)"
+                        r"|(?:===|==)\s*(?:['\"]image/svg\+xml['\"]|['\"]svg['\"])(?![^;]*?(?:throw|return|res\.(?:status|send|json)))", re.I)
 # file-serving: streaming a STORED/PROXIED object back to the client. Tightened to genuine
 # file-bytes sinks — the old rule matched a bare `getObject` token (a local coercion helper) and a
 # Prometheus `res.set('Content-Type', registry.contentType)` (the /metrics endpoint), both FPs.
diff --git a/tests/test_pentest_regressions.py b/tests/test_pentest_regressions.py
index 734194f..d6f0a54 100644
--- a/tests/test_pentest_regressions.py
+++ b/tests/test_pentest_regressions.py
@@ -328,6 +328,28 @@ def test_reuse_check_present_no_gap(self):
 
 
 class UploadSecurityTests(unittest.TestCase):  # N2
+    def test_upload_security_benign_fps(self):
+        # realistic, BENIGN code snippets that should NOT falsely trigger detections.
+        snippets = {
+            "fp1.ts": "res.status(400).json({ error: `File ${req.file.originalname} is bad` }); multer();",
+            "fp3.ts": "if (req.file.mimetype === 'image/svg+xml') throw new Error('reject'); multer();",
+            "fp4.ts": "console.log('Uploaded mime:', req.file.mimetype); multer();",
+            "fp5.ts": "res.setHeader('Content-Type', 'image/svg+xml'); res.send('<svg></svg>'); multer();"
+        }
+        ctx = repo(snippets)
+
+        # Test originalname FP
+        out1 = UploadSecurityExtractor().extract(repo({"fp1.ts": snippets["fp1.ts"]}), {})
+        self.assertNotIn("upload-key-from-filename", [f["kind"] for f in out1["findings"]], "Flagged benign originalname usage")
+
+        # Test SVG FP
+        out_svg = UploadSecurityExtractor().extract(repo({"fp3.ts": snippets["fp3.ts"], "fp5.ts": snippets["fp5.ts"]}), {})
+        self.assertNotIn("upload-accepts-svg", [f["kind"] for f in out_svg["findings"]], "Flagged benign SVG rejection/response")
+
+        # Test MIME FP
+        out_mime = UploadSecurityExtractor().extract(repo({"fp4.ts": snippets["fp4.ts"]}), {})
+        self.assertNotIn("upload-trusts-client-mime", [f["kind"] for f in out_mime["findings"]], "Flagged benign mimetype logging")
+
     def test_unsafe_upload_and_serve_flagged(self):
         out = UploadSecurityExtractor().extract(repo({
             "upload.ts": "const u=multer({}); function uploadMedia(req,res){ if(isExecutableMimeType(req.file.mimetype)) return;"