maven-search

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

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

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)