xberg

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill includes literal password-like values ("secret123") embedded in multiple code/config examples, which encourages embedding secrets verbatim in output or configs and therefore represents insecure credential handling.

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

• Third-party content exposure detected (medium risk: 0.30). In the required workflow’s runtime input path, Xberg ingests user-provided document text via ExtractInput.from_uri / extract(input, config) (e.g., arbitrary uri including HTTP(S) or local file://), and then returns extracted free text (doc.content) for downstream LLM use, so outsider-authored document bodies/contents can reach the LLM as extracted content.