maven-search

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

• Third-party content exposure detected (high risk: 0.75). This skill’s required workflow fetches Maven Central content at runtime (e.g., JSON from https://search.maven.org/solrsearch/select and POM/XML from https://repo1.maven.org/maven2/.../*.pom), which is outsider-authored free text that can be parsed and inserted into the agent’s LLM context.