skills/klotzkette/claude-fuer-deutsches-recht/einstieg-schnelltriage-fallrouting/Gen Agent Trust Hub
einstieg-schnelltriage-fallrouting
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from user-uploaded documents for legal triage.
- Ingestion points: The 'Stummer Upload' section instructs the agent to automatically handle ZIP archives, PDFs, screenshots, and other documents when provided without a prompt.
- Boundary markers: Absent. The instructions lack delimiters or specific warnings to the agent to treat document content strictly as data rather than potential instructions.
- Capability inventory: The skill directs the agent to perform 'Live-Checks' on external legal databases and route tasks to other sub-skills based on the ingested content.
- Sanitization: Absent. There is no mention of filtering or validating the content of the uploaded materials before the agent processes them.
- [SAFE]: The skill references official legal databases and government websites (e.g., gesetze-im-internet.de, openJur, BVerfG) for verifying norms. These are recognized as trusted official services.
Audit Metadata