aktenfuehrung
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 process and analyze external legal documents such as administrative acts, contracts, and court briefs to identify gaps and deadlines. This creates a surface for indirect prompt injection where instructions could be embedded within the documents to influence the agent's behavior.
- Ingestion points: External files including 'Verwaltungsakte' (administrative acts), 'Vertragsurkunden' (contracts), and 'Schriftsätze' (legal briefs).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within these external documents.
- Capability inventory: The skill does not request or use high-risk tools such as shell execution, file system writes, or arbitrary network calls; its activity is restricted to informational analysis and referencing official legal databases.
- Sanitization: There is no evidence of automated sanitization or filtering for the external content before processing.
Audit Metadata