pr-review

Find and fix code issues before publishing a PR. Single-pass review with auto-fix. Use when reviewing code changes before submission or auditing existing cod...

This skill is coherent for its stated purpose: it will read your repository (git diff, config files, source files) and apply automatic fixes above configured confidence thresholds. Things to consider before running: - Back up or commit your branch first (run on a feature branch) so you can review or revert changes. - Review the diffs after the run (git diff --stat and full diff) and run your tests before pushing. - Note the auto-fix behavior: Diff mode auto-fixes issues scoring >=70 and Audit mode >=80 — adjust your expectations accordingly. - If you don't want the agent to edit files without explicit approval, require confirmation or run the tool in a dry-run/report-only mode. - The skill is instruction-only (no external installers), reads only repo files, and requests no cloud credentials — there are no obvious indicators of secret exfiltration or out-of-scope access. - Minor naming inconsistency: documentation refers to 'pre-review' commands while the skill is named 'pr-review' — confirm command names when installing/invoking. If you want extra assurance, run it on a non-production copy of the repo first and inspect the changes before trusting it on critical branches.

Type: OpenClaw Skill Name: pr-review Version: 2.0.1 The skill is classified as suspicious due to the broad permissions granted to the AI agent, specifically `Read`, `Edit`, `Write` access to files, and `Bash(git *)` execution capabilities, as defined in `plugins/pre-review/commands/code-audit.md` and `plugins/pre-review/commands/pre-review.md`. While these permissions are necessary for the skill's stated purpose of automatically reviewing and fixing code, they represent a significant attack surface. There is no evidence of intentional malicious behavior (e.g., data exfiltration, persistence, or unauthorized remote control) within the provided instructions, but the inherent power to modify user files and execute `git` commands could be exploited if the agent's instructions were subverted.