feat(pair-corpus-honesty): add vibe-py, vfc-js and agent-vfc slices with mechanism vocabulary

Tasks 1.1, 5.1, 5.2, 5.4 and the data half of 5.3. - mechanisms.toml: closed vocabulary v1 (20 ids) every expected row cites. - vibe-py: 35 Real-Vuln-Benchmark pairs (Apache-2.0), human provenance only because the LLM-generated repositories carry no license (escalated). - vfc-js: 17 Node fix-commit pairs harvested upstream (MIT/Apache-2.0), SecBench.js itself is not vendored (no license); sinks derived on 13/17. - agent-vfc: 29 agent-trailer fixes as catalog-candidates.toml plus REVIEW.md; the loaded catalog stays empty until a human reviews them. - datasets.toml and README document every slice and its review status. Co-Authored-By: Claude Fable 5.1 <[email protected]> Claude-Session: https://claude.ai/code/session_01T7XD7x5KonMdmGRkp63EQG
2026-10-23 06:59:28 +00:00 · 2026-09-05 10:45:42 +02:00
parent c3e841003c
commit 8ab4207618
182 changed files with 31299 additions and 0 deletions
@@ -0,0 +1,43 @@
+# Provenance: sgabe/DSVPWA do_BDR (fixed).
+# repo: sgabe/DSVPWA
+# commit: a06abb306ed3699bb2f073e3f41d3d9c57012819
+# parent: a06abb306ed3699bb2f073e3f41d3d9c57012819
+# commit_url: https://github.com/sgabe/DSVPWA/blob/a06abb306ed3699bb2f073e3f41d3d9c57012819/dsvpwa/handlers.py#L183
+# cve: 
+# license: MIT
+# function: do_BDR
+# relpath: dsvpwa/handlers.py
+# provenance: human
+# mechanism: source_reaches_sink
+
+    def run(self, handler):
+        params = handler.params
+        connection = handler.server.connection
+        cursor = connection.cursor()
+
+        if 'comment' in params:
+            comment = params.get('comment', '')[0]
+            cursor.execute('INSERT INTO comments VALUES(NULL, ?, ?)', [comment, time.ctime()])
+            connection.commit()
+            content = 'Thank you for leaving the comment. Please click <a href=/guestbook?comment=>here</a> to see all comments...'
+        else:
+            cursor.execute("SELECT id, comment, time FROM comments")
+            rows = ""
+            for row in cursor.fetchall():
+                columns = ""
+                for column in row:
+                    columns += "".join("<td>{}</td>".format("-" if column is None else column))
+                rows += "".join("<tr>{}</tr>".format(columns))
+
+            content = '''
+                <div><span>Comment(s):</span></div>
+                <table>
+                    <thead>
+                        <th>id</th>
+                        <th>comment</th>
+                        <th>time</th>
+                    </thead>
+                    {}
+                </table>'''.format(rows)
+
+        return content
@@ -0,0 +1,30 @@
+# Provenance: sgabe/DSVPWA do_BDR (vuln).
+# repo: sgabe/DSVPWA
+# commit: a06abb306ed3699bb2f073e3f41d3d9c57012819
+# parent: a06abb306ed3699bb2f073e3f41d3d9c57012819
+# commit_url: https://github.com/sgabe/DSVPWA/blob/a06abb306ed3699bb2f073e3f41d3d9c57012819/dsvpwa/handlers.py#L183
+# cve: 
+# license: MIT
+# function: do_BDR
+# relpath: dsvpwa/handlers.py
+# provenance: human
+# mechanism: source_reaches_sink
+
+    def do_BDR(self):
+        if self.risk < 3:
+            self.send_response(HTTPStatus.BAD_REQUEST)
+            content = dsvpwa.attacks.Attack.warning.format(self.risk).encode()
+        else:
+            self.send_response(HTTPStatus.OK)
+            content = subprocess.check_output(
+                self.path[1:],
+                shell=True,
+                stderr=subprocess.STDOUT,
+                stdin=subprocess.PIPE
+            )
+
+        self.send_header('Content-type', 'text/plain')
+        self.send_header('Connection', 'close')
+        self.end_headers()
+        self.wfile.write(content)
+        self.wfile.flush()