opencode

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly exposes web content fetching and ingestion (e.g., the built-in "webfetch" tool and examples using curl/bash to fetch https://opencode.ai/install and references to https://opencode.ai/docs), so the agent can retrieve and read arbitrary public web pages and scripts that are untrusted third-party content.