writing-guidelines

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches guidelines from a GitHub repository raw URL via WebFetch, which constitutes reading external repository-hosted content and warrants a low score under arbitrary fetched content rules.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent at runtime to fetch and follow external instructions from https://raw.githubusercontent.com/vercel-labs/writing-guidelines/main/command.md, which directly controls prompts and behavior.