einspruch-finanzamt
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to invoke a local Python script (scripts.legal_calc.cli) via shell command, using parameters derived from user-provided input such as the assessment date. This usage pattern presents a command injection risk if the agent interpolates the input without sufficient validation or escaping.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing untrusted data from user-supplied tax assessments and dispute narratives, creating a surface for indirect prompt injection.
- Ingestion points: User-provided data for 'Bescheid' details and 'Streitpunkt' in SKILL.md.
- Boundary markers: No specific delimiters or instructions are provided to help the agent distinguish between data and instructions within user input.
- Capability inventory: The agent possesses the capability to execute a local Python script and generate structured legal responses.
- Sanitization: No sanitization or input validation logic is prescribed in the skill definition.
Audit Metadata