kommandocenter
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external legal documents (Verwaltungsakte, Vertragsurkunden, Schriftsätze, Bescheide), which constitutes an ingestion surface for untrusted data.
- Ingestion points: Processes legal documents and external evidence as defined in the 'Arbeitsweg' section.
- Boundary markers: Absent; the instructions do not specify delimiters to separate external content from system instructions.
- Capability inventory: Handover to other functional modules and template-based document generation (DOCX/PDF).
- Sanitization: No explicit sanitization or filtering of external document content is described.
- [SAFE]: The skill operates as a high-level workflow manager. It does not include any executable scripts, network-based command execution, or access to sensitive local environment variables (such as SSH keys or AWS credentials). The references to legal databases and 'live checks' are within the context of standard legal research procedures.
Audit Metadata