e-rechnung-vorsteuer

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as invoice content and company financial details, which introduces a potential vector for indirect prompt injection.
  • Ingestion points: Data enters the agent's context through the input parameters defined in SKILL.md, including company revenue, transaction types, and specific invoice data used for format and VAT checks.
  • Boundary markers: The instructions do not specify any delimiters or safety prompts to ensure the agent ignores instructions that might be embedded within the processed invoice documents.
  • Capability inventory: No dangerous capabilities such as file system modifications, network exfiltration, or shell command execution were identified in the skill's instructions or metadata.
  • Sanitization: The skill lacks explicit sanitization or validation logic for the external data it processes.
  • [SAFE]: The skill references documentation and official guidelines from trusted government domains such as bundesfinanzministerium.de and gesetze-im-internet.de. These references are informative and do not involve executable code or sensitive data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 09:13 AM