ki-vertraege
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legal guidance and report templates without any underlying code execution, scripts, or automated tool invocations.- [EXTERNAL_DOWNLOADS]: The skill references external URLs for legal research, specifically pointing to official government domains (gesetze-im-internet.de) and European Union portals (eur-lex.europa.eu). These are well-known, trusted sources for legal text.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (contract details, roles, and context) defined in the 'Eingaben' section of SKILL.md. While no explicit boundary markers or sanitization logic is described, the skill has no dangerous capabilities (no file writing, network exfiltration, or command execution) which eliminates the attack surface.
Audit Metadata