dsv-meldung-bfdi
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a process for ingesting and evaluating external data that could contain malicious instructions.
- Ingestion points: The skill instructs the agent to collect and analyze external documents including 'Verwaltungsakte, Vertragsurkunden, Schriftsätze, Bescheide, Protokolle' as described in SKILL.md.
- Boundary markers: The instructions lack specific delimiters or 'ignore embedded instructions' warnings for the processing of these external documents.
- Capability inventory: No high-risk capabilities such as arbitrary command execution, network writing, or file system modifications were detected in the skill content.
- Sanitization: There are no instructions provided for escaping, validating, or filtering the content of the external legal documents.
- [EXTERNAL_DOWNLOADS]: The skill references several well-known and official legal resources for verification purposes, including gesetze-im-internet.de, dejure.org, openJur, and the official website of the Federal Commissioner for Data Protection and Freedom of Information (bfdi.bund.de).
Audit Metadata