agb-pruefung-kaltstart
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided legal documents and materials to perform its analysis.
- Ingestion points: External documents and "material" mentioned in the "Direktstart" and "Fachkern" sections (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions that might be embedded in the analyzed documents.
- Capability inventory: The agent is instructed to generate work products such as "Prüfmatrix", "Entwurf", and "Klauselampel" based on the input.
- Sanitization: There is no mention of sanitization or validation logic for the ingested content.
- Context: This behavior is standard for a legal analysis tool and does not indicate malicious intent.
- [SAFE]: No suspicious command execution, hardcoded credentials, obfuscation, or unauthorized network operations were detected in the skill instructions.
Audit Metadata