antithesis-setup

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

• Third-party content exposure detected (high risk: 0.90). This skill's required workflow instructs the agent to load live public resources (e.g., https://api.github.com/repos/antithesishq/antithesis-sdk-cpp/tags, https://proxy.golang.org/..., https://repo.maven.apache.org/..., https://pypi.org/pypi/..., https://crates.io/api/v1/crates/..., and the https://antithesis.com/docs/... pages) and to use those responses to choose SDK versions and drive instrumentation/build decisions, which is untrusted third‑party content that can materially influence the agent's actions.