alterlab-rma-academic-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill's Agentic Protocol and Workflow (Assessment & Planning step 1) explicitly require the agent to "search the web" for target journal author guidelines and recent articles—i.e., fetch and read open/public third‑party webpages—which the agent must interpret to guide deliverables, creating a clear avenue for indirect prompt injection.