workflow-kaltstart-und-routing
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The workflow relies on processing external user data (legal mandates and files), which creates a potential surface for instructions embedded in those documents to influence the agent's behavior.
- Ingestion points: The skill instructs the agent to read "Eingang, Auftrag und maßgebliche Dateien" (Line 11, SKILL.md).
- Boundary markers: No delimiters or specific warnings to ignore instructions embedded in the processed files are defined in the instructions.
- Capability inventory: The skill is designed to draft complete legal documents, update arguments, and prepare invoices based on processed data.
- Sanitization: No sanitization, validation, or filtering logic is specified for the incoming external data.
- [NO_CODE]: The skill consists entirely of natural language instructions and documentation in Markdown format; it does not contain any scripts, binaries, or executable code.
Audit Metadata