opencode-mirror

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs cloning/pulling from the public GitHub repository https://github.com/anomalyco/opencode into vendor/opencode "for self-reference," meaning the agent will ingest and read untrusted, user-hosted content from a public third-party source.