Review committed SDK changes before push, or review a requested diff, range, branch, or PR for correctness, security, design, performance, maintainability, repository conventions, and cross-SDK consistency.
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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.
The workflow reads PR titles, bodies, and issue/PR text via GitHub integration or git diffs, which allow outsider-authored free text injection.
DataDog/dd-trace-dotnet
5769328
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.