aris-comm-lit-review

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly includes searching "web" and "broader web" (see "Source Selection" and "Retrieval Order"/"Step 1: Search External Primary Sources") and then instructs the agent to extract facts and synthesize findings from those source URLs (see "Step 2: Extract Paper-Level Facts"), meaning untrusted third‑party web content is fetched and interpreted to drive decisions and outputs.