fix(bundle): escape catalog metadata in discovery output - #3774
Merged
Conversation
Assisted-by: GitHub Copilot (model: GPT-5.6 Sol, autonomous) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Contributor
There was a problem hiding this comment.
Pull request overview
Escapes untrusted Rich markup in human-readable bundle discovery output while preserving trusted formatting and JSON output.
Changes:
- Escapes catalog, manifest, component, and overlap values in
bundle searchandbundle info. - Adds regression tests using markup-bearing metadata.
- One unescaped catalog-supplied fallback count remains.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
src/specify_cli/commands/bundle/__init__.py |
Escapes dynamic Rich output values. |
tests/contract/test_bundle_cli.py |
Tests literal rendering of markup-bearing values. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Assisted-by: GitHub Copilot (model: GPT-5.6 Sol, autonomous) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Contributor
There was a problem hiding this comment.
Review details
Comments suppressed due to low confidence (3)
src/specify_cli/commands/bundle/init.py:251
- This has the same unsafe boundary as the search heading: a catalog ID ending in
\escapes the appended[/bold cyan], so the literal value is altered and styling leaks into the rest of the output.CatalogEntry.from_dict()accepts such IDs. Append the ID as a plain-textTextspan withbold cyanstyling instead of adjoining escaped input to a markup closing tag.
f"\n[bold cyan]{_escape_markup(str(entry.id))}[/bold cyan] "
src/specify_cli/commands/bundle/init.py:188
escape()neutralizes tags inside the value, but it does not make this interpolation boundary safe: a valid catalog ID ending in\is accepted byCatalogEntry.from_dict(), and that backslash escapes the first[in the appended[/bold]. The closing tag is then rendered literally and the remaining line inherits the bold style, so the ID is still not displayed verbatim. Build the line withrich.text.Textand append the ID as a styled plain-text span rather than concatenating it with markup.
This issue also appears on line 251 of the same file.
f" [bold]{_escape_markup(str(r.entry.id))}[/bold] "
src/specify_cli/commands/bundle/init.py:196
- A source ID ending in
\escapes this adjacent[/dim], causing the closing tag to appear as text and leaving the style open. Source IDs have no character validation, so this is reachable from the local catalog config despite callingescape(). Render this complete line with markup disabled and applydimthrough thestyleargument.
f" [dim]source: {_escape_markup(str(r.source.id))}[/dim]"
- Files reviewed: 2/2 changed files
- Comments generated: 0 new
- Review effort level: Medium
Collaborator
|
Thank you! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Bundle catalog and manifest values were rendered through
console.printwithRich markup enabled. Bracketed IDs, names, roles, descriptions, authors,
licenses, source IDs, requirements, integration IDs, component labels, and
overlap descriptions were interpreted as styling instead of literal text.
This escapes every untrusted value rendered by
bundle searchandbundle infowhile preserving trusted badges, headings, policies, and JSON output.
Regression tests use a real local catalog plus a parsed manifest, with distinct
Rich tags on catalog, manifest, component, and overlap fields.
Testing
uv run specify --helpuv sync && uv run pytestFull suite: 5424 passed, 172 skipped.
AI Disclosure
GitHub Copilot (GPT-5.6 Sol) autonomously identified, implemented, tested, and
self-reviewed this change on behalf of @marcelsafin.