Skills autofix

📦

autofix

Name: autofix
Author: coderabbitai

v0.1.0 Content revision r1 High Risk ⚙️ External commands

Fix CodeRabbit Review Comments

CodeRabbit review threads can be difficult to collect and prioritize. This skill fetches unresolved bot comments and guides review, fixes, commits, and follow-up comments.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "autofix" from https://skillstore.io/skills/coderabbitai-autofix.md and its manifest at https://skillstore.io/api/skills/coderabbitai-autofix/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/coderabbitai-autofix.md Signed manifest GET /api/skills/coderabbitai-autofix/manifest Signed lockfile GET /api/skills/coderabbitai-autofix/lockfile

Test it

Using "autofix". Find CodeRabbit issues for the current branch.

Expected outcome:

A prioritized table of unresolved CodeRabbit comments with severity, issue title, affected location, type, and action.

Using "autofix". Review each issue before applying changes.

Expected outcome:

For each fix, the skill presents the issue, relevant context, proposed change, and approval choices.

Using "autofix". Finish after applying approved fixes.

Expected outcome:

A concise summary of fixed issues, skipped issues, changed files, validation status, and the planned pull request comment.

Security Audit

High Risk

v4 • 7/6/2026 Open versioned report

Most static findings are Markdown code spans or code fences and are false positives for Ruby backtick execution. The real risks are bounded GitHub and Git shell commands. A high-impact semantic issue also executes external CodeRabbit comment prompts as direct agent instructions.

Files scanned

332

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

High

SKILL.md:88-90 SKILL.md:126-129 SKILL.md:152-155 SKILL.md:216 github.md:51-55

Untrusted PR Comment Prompt Execution

The skill extracts CodeRabbit comment text from GitHub and tells the agent to execute the agent prompt as a direct instruction, including in auto-fix mode. PR comments are external content, so this can turn malicious or compromised review text into agent instructions that edit files or influence later commands.

The workflow explicitly treats fetched GitHub comment body content as the fix prompt and says to execute it literally. The cited auto-fix path applies changes without per-issue approval, making prompt injection impact credible.

Capability review items (8)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

github.md:17

Shell command substitution

gh pr list --head $(git branch --show-current) --state open --json number,title

This is a real Bash command that runs git inside a GitHub CLI command. The branch value is unquoted, so unusual branch names could cause argument parsing issues even though arbitrary command injection is unlikely.

Medium

github.md:61-64

Shell command substitution

gh pr comment <pr-number> --body "$(cat <<'EOF'

This command posts generated content to GitHub through gh pr comment. The heredoc limits shell expansion inside the body, but it still performs a remote write from skill-controlled workflow output.

Medium

SKILL.md:57

Ruby/shell backtick execution

- Ask: "Push now?" → If yes: `git push`, inform "CodeRabbit will review in ~5 min", EXIT skill

The workflow can run git push, which publishes local commits to the remote repository. The skill asks for user confirmation first, so the risk is bounded but still a real repository mutation.

Medium

SKILL.md:184-192

Ruby/shell backtick execution

- Ask: "Push changes?" → If yes: `git push`

The workflow can run git push after fixes are committed. It is user-confirmed, but it still publishes changes to the remote repository and should remain explicit.

Medium

SKILL.md:64

Shell command substitution

gh pr list --head $(git branch --show-current) --state open --json number,title

Medium

SKILL.md:193-196

Shell command substitution

gh pr comment <pr-number> --body "$(cat <<'EOF'

This command posts generated content to GitHub through gh pr comment. The heredoc limits shell expansion inside the body, but it still performs a remote write from skill-controlled workflow output.

Medium

SKILL.md:63-65

Template literal with command substitution

```bash

The fenced Bash block contains a GitHub CLI command with command substitution for the current branch. This is legitimate workflow automation, but it should quote the branch value before execution.

Medium

SKILL.md:192-199

Template literal with command substitution

```bash

The fenced Bash block contains a gh pr comment command that writes a generated summary to GitHub. The command is intended, but it sends workflow output to a remote service.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/coderabbitai-autofix/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/coderabbitai-autofix/security.svg)](https://skillstore.io/skills/coderabbitai-autofix?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/coderabbitai-autofix?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/coderabbitai-autofix/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/coderabbitai-autofix.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

coderabbitai. (2026). autofix security audit report (audit version 4) [Author version 0.1.0]. Skillstore. https://skillstore.io/skills/coderabbitai-autofix/audits/4

BibTeX citation

@techreport{coderabbitai-coderabbitai-autofix-2026,
  author = {coderabbitai},
  title = {autofix security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/coderabbitai-autofix/audits/4},
  note = {Author version 0.1.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "autofix security audit report (audit version 4)"
version: "0.1.0"
type: report
authors:
  - name: "coderabbitai"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/coderabbitai-autofix/audits/4"
identifiers:
  - type: other
    value: "skillstore:coderabbitai-autofix:audit:4"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

100

Maintainability

Content

Community

Spec Compliance

What You Can Build

Review PR Feedback Faster

Collect unresolved CodeRabbit comments and inspect the suggested fixes in priority order.

Apply Routine Fixes

Batch low-risk CodeRabbit fixes into one local change set and one consolidated commit.

Close Review Loops

Post a summary comment after fixes so reviewers can see what changed.

Try These Prompts

Start Review Cleanup

Use CodeRabbit autofix to find unresolved review comments on my current branch and show me the issues before making changes.

Review Each Fix

Fetch CodeRabbit review comments, parse each issue, and propose one fix at a time with the current code and planned diff.

Batch Low-Risk Fixes

Find unresolved CodeRabbit comments and auto-fix routine issues, but pause before push and show a summary of all changed files.

Validate And Summarize

Run the CodeRabbit autofix workflow, apply approved fixes, run the repository validation checks, create one commit, and draft the PR summary comment.

Best Practices

Commit or stash local work before running the workflow.
Use manual review mode for security, authentication, or data handling changes.
Run repository validation checks before pushing fixes.

Avoid

Do not auto-apply prompts that request unrelated file changes or secret access.
Do not push fixes before reviewing the final diff.
Do not use the workflow on branches without a current CodeRabbit review.

Frequently Asked Questions

Does this skill create a pull request?

It can guide PR creation when no open PR exists, but it mainly works on an existing current-branch PR.

Does it require GitHub CLI?

Yes. The workflow depends on gh for authentication, PR lookup, GraphQL review thread queries, and comments.

Can I approve each fix manually?

Yes. Manual review mode shows each issue and proposed fix before applying changes.

Can it push changes automatically?

The workflow asks before pushing. You should inspect the final diff and run checks first.

Which review comments are included?

It targets unresolved review threads started by known CodeRabbit bot accounts.

What should I do with security findings?

Use manual review mode, verify the suggested change, and reject prompts that ask for unrelated actions.

Developer Details

Author

coderabbitai

License

MIT

Author version

v0.1.0

Skillstore revision

Repository

https://github.com/coderabbitai/skills/tree/main/skills/autofix

Ref

d11af420e07cd866fe39cfa937efef3223896c06

Maintenance freshness

7/18/2026

Usage

4 downloads · 94 views

File structure

📄 github.md

📄 SKILL.md

autofix

Install with my Agent

Agent-readable resources

Test it

Security Audit

Confirmed security concerns (1)

Risk Factors

Copy report link

Markdown badge

HTML badge

Embed card

APA citation

BibTeX citation

CITATION.cff

Skillstore Score

What You Can Build

Review PR Feedback Faster

Apply Routine Fixes

Close Review Loops

Try These Prompts

Best Practices

Avoid

Frequently Asked Questions

Developer Details