steuerberater-briefing
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of natural language instructions and markdown content. It does not include any shell commands, scripts, or automation logic.
- [DATA_EXPOSURE]: The skill instructs the agent on how to process sensitive documents such as tax returns and contracts. However, it does not include any mechanisms for data exfiltration, unauthorized network access, or insecure storage.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving external script execution, package installation, or remote code invocation.
- [PROMPT_INJECTION]: The instructions are task-oriented and do not attempt to bypass safety filters or override the agent's core behavior in a malicious way.
- [EXTERNAL_DOWNLOADS]: While the skill mentions official sources like ELSTER and 'Gesetze im Internet' for verification, it does not perform automated downloads or include suspicious external links.
Audit Metadata