skills/klotzkette/claude-fuer-deutsches-recht/anerkennung-von-pruefungsleistungen/Gen Agent Trust Hub
anerkennung-von-pruefungsleistungen
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted data sources including emails and portal messages.
- Ingestion points: The skill explicitly processes 'Bescheid', 'Portalnachricht', 'E-Mail', and other university documents.
- Boundary markers: There are no instructions to use delimiters or ignore instructions found within these documents.
- Capability inventory: The skill generates sensitive legal documents and plans based on these inputs.
- Sanitization: No instructions are provided to sanitize or validate the content of the external documents before they are incorporated into the agent's reasoning.
Audit Metadata