writing-guidelines

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses WebFetch to retrieve free-form guideline text from a public GitHub URL at runtime, which is outsider-authored content that becomes LLM-readable context for the review.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs fetching runtime guidelines from https://raw.githubusercontent.com/vercel-labs/writing-guidelines/main/command.md and using that fetched content to control the agent's checks and output format, so the URL is a runtime external dependency that directly controls agent prompts/behavior.