skill-builder

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

• Third-party content exposure detected (high risk: 0.80). The skill's reference documentation (see "Dynamic Context Injection" in reference.md) explicitly shows using !`command`` to fetch live API responses and examples/allowed-tools that include WebSearch/WebFetch, meaning the skill can ingest open/public web or API content which Claude will receive and act on, enabling indirect prompt injection.