skills/klotzkette/claude-fuer-deutsches-recht/dsv-risikobewertung-enisa-schweregrad/Gen Agent Trust Hub
dsv-risikobewertung-enisa-schweregrad
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed of markdown instructions intended to guide an AI agent through a legal reasoning process. There are no scripts, binaries, or automated command-line executions involved.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied incident details to perform its risk assessment. This represents an attack surface for indirect prompt injection if the incident data contains malicious instructions. However, the skill lacks dangerous capabilities such as file system modification, credential access, or arbitrary network requests that could be leveraged for an exploit. No explicit boundary markers or sanitization steps are defined for the input data.
- [EXTERNAL_DOWNLOADS]: The instructions recommend verifying legal norms via official and well-known legal databases (such as gesetze-im-internet.de and openJur). These references are contextual and target authoritative, trusted public legal resources.
Audit Metadata