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.deandgesetze-im-internet.de. These references are informative and do not involve executable code or sensitive data exfiltration.
Audit Metadata