review-pr
Deep code review of a single open PR in nrwl/nx. Checks the PR out only inside an isolated sandbox, then runs four fixed reviewers: implementation (correctness, errors, types, performance), verification (tests, ticket grounding, comments, and docs), approach, and security. A reproduce-verifier executes a runnable repro only when verification identifies one. The skill saves a GitHub-flavored draft to ~/.nx-pr-reviews/<NUMBER>.md and never posts it. Claude reads/executes PR code only through the sandbox CLI; credentials never enter the sandbox.
67
82%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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
In Step 2 the orchestrator fetches outsider-authored free text from the PR body/Linear issue description and comments (via `mcp__plugin_linear_linear__get_issue` / `..._list_comments`), then carries that text into dispatched agents’ context; this is a direct runtime prompt-injection surface because attacker-controlled content is ingested without selecting a specific item beyond the PR number.
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 invokes .claude/tools/sandbox start --checkout https://github.com/nrwl/nx at runtime (SKILL.md:158), which fetches that remote repository and then runs the PR code inside the sandbox, so this URL is used at runtime to fetch and execute external code.
- Audited
- 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.