writing-guidelines

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

• Third-party content exposure detected (high risk: 0.95). The skill uses WebFetch to retrieve guidelines from a public GitHub URL at runtime, and that fetched free-form text is then ingested into the agent’s LLM context to drive the review (outsider-authored public web content).

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

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