skills/klotzkette/claude-fuer-deutsches-recht/1-gwb-kartellverbot-nationale-pruefung/Gen Agent Trust Hub
1-gwb-kartellverbot-nationale-pruefung
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as contracts, notices, and evidentiary documents. 1. Ingestion points: Data enters the agent context via documents, numbers, and register data specified in the Startfragen section of SKILL.md. 2. Boundary markers: The instructions do not define delimiters or warnings to ignore embedded instructions within the ingested documents. 3. Capability inventory: The skill identifies legal norms and evaluates evidence but does not contain capabilities for file writing, system commands, or network exfiltration. 4. Sanitization: No explicit sanitization or filtering logic is provided for the external content.
- [NO_CODE]: The skill contains only natural language instructions in markdown format and does not include any scripts, executable files, or package dependencies.
Audit Metadata