abzweigung-aus-patentanmeldung
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 evaluate external legal documents provided by the user, which establishes a surface for indirect prompt injection.
- Ingestion points: The skill instructs the agent to collect and analyze documents such as 'Gebrauchsmusteranmeldung' (utility model application), 'Schutzschrift' (protective brief), and 'Löschungsantrag' (cancellation request) as described in the 'Arbeitsweg' section of SKILL.md.
- Boundary markers: There are no instructions provided to the agent to use delimiters or specific safety instructions to ignore potential commands embedded within the processed legal documents.
- Capability inventory: The skill body references a 'Live-Check' for updated regulations and administrative practices, implying the use of external search or retrieval tools to verify information.
- Sanitization: The instructions do not include steps for sanitizing, escaping, or validating the text content of the ingested evidence or documents.
Audit Metadata