Fix injection vulnerability in API generation script

[phbrgnomo]

Changing subprocess.check_output to subprocess.run enhances security by avoiding shell invocation and safely passing arguments.

Summary by Sourcery

Enhancements:

• Replace subprocess.check_output with subprocess.run in git helper functions to avoid shell invocation and safely capture command output.

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Refactors git metadata helpers in docs/generate_api.py to use subprocess.run instead of subprocess.check_output, improving argument safety and error handling for git commands.

File-Level Changes

Change	Details	Files
Refactor git helper functions to use subprocess.run for safer subprocess execution and clearer handling of stdout.	Replace subprocess.check_output with subprocess.run(check=True, stdout=subprocess.PIPE, text=True) in git_head_commit to avoid implicit shell behavior and work directly with a CompletedProcess object Strip stdout from the CompletedProcess to preserve existing return values for git_head_commit Replace subprocess.check_output with subprocess.run in git_project_root and assign completed.stdout to the existing variable used for path normalization Preserve existing exception handling for OSError and subprocess.CalledProcessError while relying on check=True for failure detection	docs/generate_api.py

---

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.

[sourcery-ai]

Hey - I've found 2 security issues, and left some high level feedback:

Security issues:

• Detected subprocess function 'run' without a static string. If this data can be controlled by a malicious actor, it may be an instance of command injection. Audit the use of this call to ensure it is not controllable by an external resource. You may consider using 'shlex.escape()'. (link)
• Detected subprocess function 'run' without a static string. If this data can be controlled by a malicious actor, it may be an instance of command injection. Audit the use of this call to ensure it is not controllable by an external resource. You may consider using 'shlex.escape()'. (link)

General comments:

• The security rationale in the comments and PR description is slightly misleading, since the original subprocess.check_output already used an argument list without shell=True; consider clarifying that this is primarily a refactor (e.g., standardizing on subprocess.run) rather than a security hardening.
• The new comments above both git_head_commit and git_project_root are nearly identical and somewhat verbose; consider reducing duplication or tightening the wording to focus on why subprocess.run is preferred in this codebase.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The security rationale in the comments and PR description is slightly misleading, since the original `subprocess.check_output` already used an argument list without `shell=True`; consider clarifying that this is primarily a refactor (e.g., standardizing on `subprocess.run`) rather than a security hardening.
- The new comments above both `git_head_commit` and `git_project_root` are nearly identical and somewhat verbose; consider reducing duplication or tightening the wording to focus on why `subprocess.run` is preferred in this codebase.

## Individual Comments

### Comment 1
<location> `docs/generate_api.py:1153` </location>
<code_context>
        completed = subprocess.run(process_args, stdout=subprocess.PIPE, text=True, check=True)
</code_context>

<issue_to_address>
**security (python.lang.security.audit.dangerous-subprocess-use-audit):** Detected subprocess function 'run' without a static string. If this data can be controlled by a malicious actor, it may be an instance of command injection. Audit the use of this call to ensure it is not controllable by an external resource. You may consider using 'shlex.escape()'.

*Source: opengrep*
</issue_to_address>

### Comment 2
<location> `docs/generate_api.py:1171` </location>
<code_context>
            completed = subprocess.run(cmd, stdout=subprocess.PIPE, text=True, check=True)
</code_context>

<issue_to_address>
**security (python.lang.security.audit.dangerous-subprocess-use-audit):** Detected subprocess function 'run' without a static string. If this data can be controlled by a malicious actor, it may be an instance of command injection. Audit the use of this call to ensure it is not controllable by an external resource. You may consider using 'shlex.escape()'.

*Source: opengrep*
</issue_to_address>

---

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.}