antithesis-workload

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly tells the agent to read external public documentation (for example the snouty README at https://raw.githubusercontent.com/antithesishq/snouty/refs/heads/main/README.md and multiple pages under https://antithesis.com/docs/) via the antithesis-documentation/snouty docs, which the agent is expected to ingest and use to make tooling and assertion decisions—exposing it to untrusted third‑party web content that can influence actions.