ustva-buchhaltung-simulation
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources including incoming invoices, electronic invoices (E-Rechnungen), and bank statements, which could potentially contain malicious instructions.
- Ingestion points: The skill reads data from local registers such as
kanzlei-allgemein-buchhaltung-kontenand processes external files like credit card statements and invoices at runtime. - Boundary markers: There are no explicit instructions or delimiters in the workflow to separate the content of these documents from the agent's internal logic, making it susceptible to accidental instruction execution if a document contains command-like text.
- Capability inventory: The skill possesses the capability to read local accounting registers and write various output reports to the
assets/templates/directory. - Sanitization: The instructions do not specify any validation, filtering, or sanitization of the external financial data before it is processed and used to generate reports.
Audit Metadata