architect-employment-checker-system

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt embeds plaintext default credentials (MINIO_ROOT_USER/minio and MINIO_ROOT_PASSWORD/minio123) which will lead the LLM to generate configs or commands containing those secrets verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests arbitrary user-provided PDFs via the required POST /documents/upload (stored in S3/MinIO) and then runs preprocessing, clause-extraction, validation, and report-synthesis steps that the agent will read and act on, so untrusted third-party document content can influence downstream decisions.