skills/klotzkette/claude-fuer-deutsches-recht/abgrenzung-konventionelle-software-vs-ki-system/Gen Agent Trust Hub
abgrenzung-konventionelle-software-vs-ki-system
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown-based instructions and classification logic. No executable code such as Python, JavaScript, or shell scripts is included or referenced in the file.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests software descriptions from users within the agent context defined in SKILL.md to perform its classification task. Boundary markers for these inputs are absent in the instructions. The capability inventory for this skill is empty, as there are no executable scripts, subprocess calls, or tool-use definitions included in the skill. Sanitization of input data is not explicitly performed.
- [SAFE]: The skill references established legal information domains like gesetze-im-internet.de and dejure.org for the purpose of identifying official statutory texts. These are recognized public resources for legal research and do not represent a security risk.
Audit Metadata