skills/klotzkette/claude-fuer-deutsches-recht/spezial-erstellung-red-team-und-qualitaetskontrolle/Gen Agent Trust Hub
spezial-erstellung-red-team-und-qualitaetskontrolle
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process external, user-provided documents such as rental contracts, utility bills, and legal notices to generate analysis and drafts. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the data.
- Ingestion points: Processes user-supplied documentation, including contracts, notices, and messages in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore commands potentially embedded in the external data.
- Capability inventory: The skill generates structured legal drafts, memos, and court complaint outlines.
- Sanitization: No evidence of sanitization, escaping, or validation of the input data is present.
Audit Metadata