skills/klotzkette/claude-fuer-deutsches-recht/ki-vo-hochrisiko-konformitaetsbewertung/Gen Agent Trust Hub
ki-vo-hochrisiko-konformitaetsbewertung
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external data in the form of compliance dossiers and technical documentation.
- Ingestion points: Section 2 specifies ingestion of 'Zweckbestimmung' (intended use), 'Risikoeinstufung' (risk classification), 'Konformitätserklärung' (declaration of conformity), and other external documentation files.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the analyzed documents.
- Capability inventory: The skill contains no executable scripts, tool invocations, network operations, or file-writing capabilities.
- Sanitization: No explicit sanitization of external content is mentioned.
- Note: While the skill has an attack surface for indirect prompt injection, it possesses no capabilities to act upon malicious instructions, rendering the risk negligible.
Audit Metadata