global-technical-writing

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly says it will fetch the source page when the local reference lacks the prompt and references the external prompt page https://technical-writing.dev/tutorial/review-prompt.html, meaning runtime-fetched content could be injected verbatim into agent prompts.