anhoerung-vor-bescheid
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists exclusively of Markdown-formatted instructions and text templates. It does not include any Python scripts, JavaScript files, shell scripts, or binary executables.
- [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection as it encourages the agent to ingest external legal documents (e.g., NKR-Stellungnahme, Digitalcheck-Bericht) and perform live checks on legal databases (e.g., openJur, dejure.org). However, since the skill does not grant the agent high-privilege capabilities such as file system modifications or remote code execution, the risk is minimal and inherent to the skill's purpose as a research assistant.
Audit Metadata