writer-agent

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts arbitrary URLs and runs them through the converter (Step 1 "URL (web page) → wa-convert {url}") producing docs/generated/.../content.md which the main agent and subagents are required to read (e.g., Tier templates and references/article-writer-prompt.md, references/context-extractor-prompt.md) as part of the core workflow, so untrusted public webpages can be ingested and influence subsequent tool actions and decisions.