Verify the technical accuracy of a vscode-docs pull request against the VS Code source code in microsoft/vscode and microsoft/vscode-copilot-chat. Use when reviewing a docs PR for factual correctness — setting names, command IDs, default values, API shapes, keybindings, versioned availability, and described behavior.
79
100%
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.
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 required workflow ingests outsider-authored free text from the target PR body/diff (via `gh pr view ... --json ... files,body` and `gh pr diff <number>`), i.e., content written by someone other than the operating user is read into the LLM context for analysis.
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.
The skill issues GH API calls at runtime to read repository files (e.g., `gh api repos/microsoft/vscode/contents/<path>?ref=main`), which injects raw remote source content into the agent's context to drive its verification logic.
66977a9
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.