abrechnung-und-buchauszug
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted data which could contain malicious instructions.
- Ingestion points: The skill explicitly instructs the agent to process documents, tables, contracts, tickets, logs, emails, and chat history (identified in the 'Kaltstartfragen' section of SKILL.md).
- Boundary markers: There are no explicit instructions for the agent to use delimiters or to ignore instructions embedded within the provided documents.
- Capability inventory: The skill does not include any executable scripts, shell commands, or network operations. Its primary function is to generate text-based outputs such as memos, tables, and checklists.
- Sanitization: No specific filtering or sanitization procedures for the external content are mentioned.
- [NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata without any accompanying source code, scripts, or binaries.
Audit Metadata