🛡️ Sentinel: [CRITICAL] Fix arbitrary code execution in AST type evaluation

[bashandbone]

🚨 Severity: CRITICAL
💡 Vulnerability: The _safe_eval_type function in src/codeweaver/core/di/container.py validated type hints by parsing them as AST trees and manually traversing them. However, it permitted generic ast.Call nodes without verifying the identity of the function being called. Because these AST nodes are later evaluated using eval(), this allowed the arbitrary execution of any callable present in the module's global namespace, leading to a critical Arbitrary Code Execution (ACE) vulnerability.
🎯 Impact: Malicious or unvalidated type hints could execute unauthorized functions, potentially compromising the host system or exposing sensitive environment variables.
🔧 Fix: Added a custom visit_Call method to the TypeValidator class. This method strictly evaluates the func attribute of ast.Call nodes and restricts execution to a specific whitelist of known, safe dependency injection and metadata functions used by the framework (Depends, depends, Field, PrivateAttr, Tag, Parameter).
✅ Verification: Ran format, lint, and the entire test suite which completed successfully with no regressions. Verified that ast.Call dynamically evaluates the correct dependencies without allowing unauthorized standard library or built-in function executions. Logged in .jules/sentinel.md.

---

PR created automatically by Jules for task 3584191746221468630 started by @bashandbone

Summary by Sourcery

Harden AST-based type hint evaluation in the DI container to prevent arbitrary code execution from untrusted type strings and document the incident in Sentinel notes.

Bug Fixes:

• Restrict callable nodes in _safe_eval_type AST validation to a whitelist of known-safe DI and metadata helpers, preventing arbitrary function execution during type evaluation.

Documentation:

• Add a Sentinel security entry describing the arbitrary code execution vulnerability in _safe_eval_type, its root cause, and the whitelisting-based mitigation.

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[sourcery-ai]

Reviewer's Guide

Restricts AST-based type evaluation in the DI container to only allow a small whitelist of framework-safe function calls inside type hint expressions, closing a critical arbitrary code execution vulnerability, and documents the incident in the Sentinel log.

Sequence diagram for safe type hint evaluation with whitelisted ast.Call

sequenceDiagram
    participant Container
    participant ast
    participant TypeValidator
    participant eval

    Container->>ast: parse(type_str, mode="eval")
    ast-->>Container: tree
    Container->>TypeValidator: visit(tree)
    TypeValidator->>TypeValidator: generic_visit(node)
    TypeValidator->>TypeValidator: visit_Call(ast.Call)
    alt allowed function
        TypeValidator->>TypeValidator: generic_visit(node)
        TypeValidator-->>Container: validation ok
        Container->>eval: eval(compile(tree, filename, mode), globalns)
        eval-->>Container: evaluated_type
    else forbidden function
        TypeValidator-->>Container: raise TypeError
        Container-->>Container: handle TypeError (return None)
    end

Loading

File-Level Changes

Change	Details	Files
Harden AST validation in _safe_eval_type to block arbitrary function execution from type hints while still allowing known DI/metadata helpers.	Adds a high-complexity noqa annotation to _safe_eval_type to suppress C901 complexity warnings while extending its validator. Introduces a visit_Call method on TypeValidator that restricts ast.Call nodes to a whitelist of safe functions (Depends, depends, Field, PrivateAttr, Tag, Parameter). Implements strict checks for ast.Name, ast.Attribute, and other callable node types, raising TypeError for any non-whitelisted calls, then defers to generic_visit for traversal of allowed calls. Preserves existing AST validation behavior for other node types and error handling around TypeValidator().visit(tree).	src/codeweaver/core/di/container.py
Document the newly discovered ACE vulnerability in the project’s Sentinel security log.	Adds a dated Sentinel entry describing the unvalidated ast.Call vulnerability in _safe_eval_type, its impact, and the need for strict whitelisting of callable nodes.	.jules/sentinel.md

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[github-actions]

🤖 Hi @bashandbone, I've received your request, and I'm working on it now! You can track my progress in the logs for more details.

[github-actions]

🤖 I'm sorry @bashandbone, but I was unable to process your request. Please see the logs for more details.

[sourcery-ai]

Hey - I've left some high level feedback:

• Consider hoisting the allowed_funcs set out of visit_Call into a module-level or enclosing-scope constant so it can be reused and kept in sync with the DI/metadata API in a single place.
• Since _safe_eval_type is now complex enough to require # noqa: C901, it may be worth extracting TypeValidator into a separate, named class at module scope to make the function smaller and easier to follow.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- Consider hoisting the `allowed_funcs` set out of `visit_Call` into a module-level or enclosing-scope constant so it can be reused and kept in sync with the DI/metadata API in a single place.
- Since `_safe_eval_type` is now complex enough to require `# noqa: C901`, it may be worth extracting `TypeValidator` into a separate, named class at module scope to make the function smaller and easier to follow.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}