ai-act-art-6-hochrisiko-ki
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to analyze external, potentially untrusted documentation such as provider records, data flow descriptions, and system logs.
- Ingestion points: Instructions in section 1.1 and 1.3 involve reading purpose descriptions, provider documents, and legislative updates.
- Boundary markers: The skill lacks explicit markers or delimiters to isolate untrusted input from the agent's core instructions.
- Capability inventory: The skill is limited to analysis and reporting; it does not define or call tools for file modification, network exfiltration, or shell execution.
- Sanitization: No validation or sanitization processes are defined for the ingested documents.
Audit Metadata