Skip to content

Fix XSS in EncodingVisualizer HTML attributes #2216

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
varneeth01 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix XSS in EncodingVisualizer HTML attributes #2216

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions bindings/python/py_src/tokenizers/tools/visualizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -219,7 +219,7 @@ def consecutive_chars_to_html(
stoken = encoding.tokens[first.token_ix]
# special tokens are represented as empty spans. We use the data attribute and css
# magic to display it
return f'<span class="special-token" data-stoken={stoken}></span>'
return f'<span class="special-token" data-stoken="{html.escape(stoken, quote=True)}"></span>'
# We're not in a special token so this group has a start and end.
last = consecutive_chars_list[-1]
assert first.char_ix is not None
Expand Down Expand Up @@ -255,7 +255,7 @@ def consecutive_chars_to_html(
css = f'''class="{" ".join(css_classes)}"'''
data = ""
for key, val in data_items.items():
data += f' data-{key}="{val}"'
data += f' data-{key}="{html.escape(str(val), quote=True)}"'
span_text = html.escape(span_text)
return f"<span {css} {data} >{span_text}</span>"

Expand All @@ -272,7 +272,7 @@ def __make_html(text: str, encoding: Encoding, annotations: AnnotationList) -> s
anno = annotations[cur_anno_ix]
label = anno.label
color = label_colors_dict[label]
spans.append(f'<span class="annotation" style="color:{color}" data-label="{label}">')
spans.append(f'<span class="annotation" style="color:{color}" data-label="{html.escape(label, quote=True)}">')

for cs in char_states[1:]:
cur_anno_ix = cs.anno_ix
Expand All @@ -296,7 +296,7 @@ def __make_html(text: str, encoding: Encoding, annotations: AnnotationList) -> s
anno = annotations[cur_anno_ix]
label = anno.label
color = label_colors_dict[label]
spans.append(f'<span class="annotation" style="color:{color}" data-label="{label}">')
spans.append(f'<span class="annotation" style="color:{color}" data-label="{html.escape(label, quote=True)}">')
prev_anno_ix = cur_anno_ix

if cs.partition_key() == current_consecutive_chars[0].partition_key():
Expand Down