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.md explicitly instructs the agent to browse and clone public GitHub repositories (https://github.com/aptos-labs/aptos-core and https://github.com/aptos-labs/daily-move) and to read/interpret their example source files as part of its workflow, so it ingests open/public third‑party content that could influence subsequent tool use or decisions.