skills/klotzkette/claude-fuer-deutsches-recht/akte-anlegen-und-aktenzeichen-zuordnen/Gen Agent Trust Hub
akte-anlegen-und-aktenzeichen-zuordnen
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external legal documents which may contain untrusted content.
- Ingestion points: The skill ingests external data from sources described as "eingehendem Schriftstueck" (incoming documents), "Verwaltungsakte" (administrative files), "Vertragsurkunden" (contracts), and "Schriftsätze" (pleadings) in the 'Arbeitsweg' and 'Ablauf' sections of
SKILL.md. - Boundary markers: The instructions do not define clear delimiters or provide instructions to the agent to disregard instructions potentially embedded within the ingested legal documents.
- Capability inventory: The skill has the capability to generate structured legal work products, including a "Mandatsblatt" (mandate sheet), "Aktenstruktur" (file structure), and "Übergabeliste" (transfer list), which are influenced by the ingested data.
- Sanitization: There is no evidence of sanitization, escaping, or filtering logic applied to the external content before it is processed by the agent.
Audit Metadata