skills/klotzkette/claude-fuer-deutsches-recht/spezial-quellen-schriftsatz-brief-und-memo-bausteine/Gen Agent Trust Hub
spezial-quellen-schriftsatz-brief-und-memo-bausteine
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional content for an AI agent to act as a legal drafting assistant. It contains no executable code, network operations, or external dependencies.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided documents (e.g., contracts, register excerpts, and correspondence) to generate legal drafts. While this presents an attack surface for indirect prompt injection via the provided data, the skill possesses no capabilities for external communication or file system modification that could be exploited.
- Ingestion points: User-supplied documents, register excerpts, and case facts (referenced in 'Kaltstart' section of SKILL.md).
- Boundary markers: The instructions do not define specific delimiters to isolate user-provided data from agent instructions.
- Capability inventory: The skill is restricted to text generation and does not invoke subprocesses, write files, or perform network operations.
- Sanitization: No explicit content sanitization or validation logic is defined in the instructions.
Audit Metadata