-
-
Notifications
You must be signed in to change notification settings - Fork 807
fix(security): bump vulnerable dependencies to safe minimum versions #1149
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.
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
base: main
Are you sure you want to change the base?
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -38,7 +38,7 @@ docs = [ | |
| "mkdocs>=1.5.0", | ||
| ] | ||
| docs-scripts = [ | ||
| "crawl4ai>=0.4.0", | ||
| "crawl4ai>=0.8.0", | ||
| "playwright>=1.40.0", | ||
| "lancedb>=0.4.0", | ||
| "sentence-transformers>=2.2.0", | ||
|
|
@@ -64,6 +64,14 @@ examples = [] | |
|
|
||
| [tool.uv] | ||
| package = false | ||
| # Security: constrain vulnerable transitive dependencies to safe minimum versions | ||
| constraint-dependencies = [ | ||
| "authlib>=1.6.7", # GHSA-7wc2-qxgw-g8gg: JWT alg:none bypass (HIGH) | ||
| "cryptography>=46.0.5", # GHSA-r6ph-v2qm-q3c2: ECDH subgroup attack (HIGH) | ||
| "urllib3>=2.6.3", # GHSA-38jv-5279-wg99: decompression bomb bypass (HIGH) | ||
| "werkzeug>=3.1.6", # GHSA-29vq-49wr-vm6x: Windows device names (MODERATE) | ||
| "aiohttp>=3.13.3", # GHSA-jj3x-wxrx-4x23, GHSA-6jhg-hg63-jvvf: DoS (MODERATE/LOW) | ||
| ] | ||
|
Comment on lines
+67
to
+74
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. 🧩 Analysis chain🏁 Script executed: #!/bin/bash
# Find published package manifests that depend on fastmcp.
rg -n -C2 '"fastmcp[^"]*"' --glob '**/pyproject.toml'
printf '\n--- security floors published in package metadata ---\n'
rg -n -C1 '"(authlib|cryptography|urllib3|werkzeug|aiohttp)[^"]*"' --glob '**/pyproject.toml'Repository: trycua/cua Length of output: 3305 Root-only
🤖 Prompt for AI Agents |
||
|
|
||
| [tool.uv.workspace] | ||
| members = [ | ||
|
|
||
Large diffs are not rendered by default.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧩 Analysis chain
🏁 Script executed:
Repository: trycua/cua
Length of output: 1468
🏁 Script executed:
Repository: trycua/cua
Length of output: 269
🏁 Script executed:
Repository: trycua/cua
Length of output: 84
🌐 Web query:
Gradio 6 migration guide allow_tags default behavior gr.Chatbot💡 Result:
In Gradio 6,
gr.Chatbot’sallow_tagsdefault changed fromFalse→True, meaning chatbot messages will no longer strip tag-like content by default (to better support LLM outputs that include HTML/custom tags such as<thinking>). If you want the pre–Gradio 6 behavior (remove all tags), set it explicitly:This change is called out in the Gradio 6 migration guide and tracked in the changelog/PR. [1], [2], [3]
🏁 Script executed:
Repository: trycua/cua
Length of output: 1398
🏁 Script executed:
Repository: trycua/cua
Length of output: 36
🏁 Script executed:
Repository: trycua/cua
Length of output: 861
Gradio 6 changes
gr.Chatbot()defaults; explicitallow_tagshandling needed.Upgrading to
gradio>=6.7.0changesgr.Chatbot()'s default behavior:allow_tagsnow defaults toTrueinstead ofFalse. This means chatbot messages will preserve tag-like content (e.g.,<thinking>,<tool_call>) rather than stripping them.Two instantiations are affected and do not set
allow_tagsexplicitly:libs/python/agent/agent/ui/gradio/ui_components.py:565- baregr.Chatbot()libs/python/agent/agent/human_tool/ui.py:477-gr.Chatbot(label="Conversation", height=500, buttons=["copy"])Please either set
allow_tagsexplicitly to the desired behavior, or add regression tests with representative model/tool responses to validate the new behavior is acceptable before merging.🤖 Prompt for AI Agents