reisevermittlung-informationspflichten
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as booking details, AGBs, and correspondence, which could contain malicious instructions designed to influence the agent's legal analysis.
- Ingestion points: Defined in
SKILL.mdunder the "Eingaben" section, specifically for items like "Buchungsbestätigung", "AGB", and "Schriftverkehr". - Boundary markers: The skill instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when processing user-provided documents.
- Capability inventory: The skill uses a multi-agent architecture (researcher, drafter, reviewer) to perform legal subsumption and draft formal claim letters.
- Sanitization: No explicit content sanitization, validation, or filtering of external legal content is described in the provided instructions.
Audit Metadata