local-review
Code review the current PR (or branch diff against main) for bugs, security, and AGENTS.md compliance. MUST use when asked to review code.
75
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly requires relaying the subagent's findings verbatim and then posting that output via gh commands as PR comments, which forces the agent to emit any secrets the subagent discovered (e.g., API keys, tokens) into its outputs/requests.
Low
Low-risk findings.
1 low severity finding. 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
The required workflow invokes a fresh-context subagent that reads `REVIEW.md`, `AGENTS.md`, and—critically—fetches PR contents via `gh pr diff` / `gh pr view` (outsider-authored GitHub PR code/text), which then becomes readable LLM input to the subagent (indirect prompt-injection risk).
- Repository
- windmill-labs/windmill
- Commit
33d2845
- 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.