01-akte-erstdurchsicht-strafsache
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection as it is specifically designed to analyze external case files, such as indictments and suspect statements, which are untrusted data sources.
- Ingestion points: The skill in
SKILL.mdprocesses external documents including 'Anklage' (indictments), 'Einlassung' (statements), and 'Belege' (evidence). - Boundary markers: Absent. There are no instructions or system delimiters defined to isolate the processed text from the agent's core instructions.
- Capability inventory: The skill in
SKILL.mdhas the capability to generate high-stakes legal outputs including 'Urteilsgründe' (judgments), 'Strafbefehle' (penal orders), and 'Eröffnungsbeschlüsse' (opening orders). - Sanitization: Absent. No validation or filtering mechanisms are described for the external content before it is interpolated into the reasoning process.
Audit Metadata