dsv-sofortmassnahmen-checkliste
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to process external material ("Wenn Material vorliegt, lies es zuerst...") to form hypotheses and checklists. This creates a surface for indirect prompt injection if the processed documents contain malicious instructions.
- Ingestion points: The skill explicitly instructs the agent to ingest and analyze user-provided material (documents, reports, or logs related to a data breach) in the 'Direktstart' and 'Arbeitsweg' sections of
SKILL.md. - Boundary markers: The skill lacks explicit boundary markers or instructions for the agent to ignore or delimit instructions found within the analyzed material.
- Capability inventory: The skill does not define any code execution, file system write, or network-bound capabilities; its primary output is a text-based prioritized measures list.
- Sanitization: No sanitization or filtering logic is specified for the ingested content.
Audit Metadata