prepare-pr

Prepare a GitHub PR for merge by rebasing onto main, fixing review findings, running gates, committing fixes, and pushing to the PR head branch. Use after /reviewpr. Never merge or push to main.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Low

W011: Third-party content exposure detected (indirect prompt injection risk).

What this means

The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.

Why it was flagged

The skill explicitly runs `gh pr view` and `git fetch origin pull/<PR>/head:pr-<PR>` and reads the PR body/branch files (and uses them to fix review items and drive commits/tests), which ingests untrusted, user-generated content from GitHub PRs that can materially influence subsequent git/tool actions.

Report incorrect finding

Low

W012: Unverifiable external dependency detected (runtime URL that controls agent).

What this means

The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.

Why it was flagged

The skill uses the PR head repository URL (added as "$head_repo_url.git" from gh pr view) at runtime to fetch the PR branch (git fetch/reset) and then runs build/test steps (pnpm install/build/test), so remote repository code will be retrieved and executed — flagging the PR head repo URL (e.g., https://github.com/owner/repo.git).

Report incorrect finding

Repository: deepgram/dglabs-deepclaw
Path: .agents/skills/prepare-pr/SKILL.md
Commit: ec8d4f8

Audited: 1 month ago
Security analysis

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.