skills/klotzkette/claude-fuer-deutsches-recht/dsv-risikobewertung-edsa-leitlinie/Gen Agent Trust Hub
dsv-risikobewertung-edsa-leitlinie
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to verify legal citations using well-known German and European legal databases, including gesetze-im-internet.de, dejure.org, openJur, and official court databases (BVerfG, BGH, EuGH). These are established public resources for legal research.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided documentation related to data protection incidents, creating a potential surface for indirect prompt injection.
- Ingestion points: User descriptions of data breach incidents, technical/organizational measures, and provided evidence (e.g., contracts, protocols, administrative acts) as specified in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the analyzed documents.
- Capability inventory: The skill does not contain any scripts, subprocess calls, file-write operations, or arbitrary network capabilities. Its function is limited to analysis and text generation based on provided guidelines.
- Sanitization: No specific sanitization or filtering logic is defined for the external content being processed.
Audit Metadata