review-sendmsg

Perform detailed Python code reviews identifying bugs, security risks, test gaps, and maintainability issues in diffs, patches, or pull requests.

This package contains runnable scripts that will (if configured) send repository diffs to an external LLM endpoint and post logs/notifications to Telegram, but the registry metadata does not declare those environment variables or behaviors. Before installing or running: 1) Do not provide your production LLM API key or real repo credentials until you verify the maintainer and endpoint (LLM_API_URL points to a third-party host). 2) Inspect PROJECTS_DATA to ensure it doesn't point to sensitive/private git URLs. 3) If you need only interactive review functionality, consider removing or disabling the review_runner/telegram parts. 4) Run the scripts in an isolated/test environment (no access to private secrets or production repos). 5) Ask the author/owner for clarification: why the description says 'Python review' while the code reviews many languages, and why required env vars were omitted from the skill metadata. If you cannot verify these answers, treat the skill as untrusted and avoid supplying secrets or connecting it to sensitive repositories.

Type: OpenClaw Skill Name: skill-review-sendmsg Version: 1.0.0 The skill bundle provides a functional framework for automated code reviews across multiple languages (PHP, JS, TS, SQL, Shell). It utilizes local linters (e.g., php -l, node --check) and integrates with the DeepSeek LLM API to analyze git diffs, reporting results via Telegram. While it executes shell commands via subprocess and communicates with external APIs, these actions are strictly aligned with its stated purpose of code auditing and notification, with no evidence of malicious intent, credential theft, or unauthorized data exfiltration.