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 directs the agent to load and parse public third‑party documentation and APIs (see "Documentation Grounding" in SKILL.md and language reference files such as references/language/cpp.md and references/language/python.md which instruct fetching URLs like https://api.github.com/... , https://pypi.org/pypi/... , and repo.maven.apache.org to determine SDK versions and build instructions), so untrusted external content is read and used to drive build/instrumentation decisions.