verbandsklage-zulaessigkeit
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to invoke a local Python module (
scripts.legal_calc.cli) for performing legal deadline and financial calculations. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external legal data, creating a surface for indirect prompt injection attacks.
- Ingestion points: Processes user-provided legal complaints (Klageschrift), financial disclosure documents (Mittelherkunft), and third-party financing agreements.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external legal text as untrusted data.
- Capability inventory: The skill possesses the ability to execute shell commands via a local Python CLI tool.
- Sanitization: No evidence of input validation, sanitization, or escaping of the external legal documents is present before the data is processed or used by the calculations script.
Audit Metadata