eval

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to retrieve external Strands Evals SDK documentation and/or clone the public GitHub repository (git clone https://github.com/strands-agents/evals) and to read those source/docs as part of implementation, which are untrusted public third‑party sources the agent will ingest and interpret.