search-aptos-examples

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to browse and read public GitHub repositories (e.g., https://github.com/aptos-labs/aptos-core and https://github.com/aptos-labs/daily-move) and online docs, so it will fetch and interpret open third‑party content that could contain untrusted/user‑generated material.