cloud-auftragsverarbeitung
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external documents, specifically legal contract drafts and technical measures documentation.
- Ingestion points: The skill explicitly requests "AVV-Entwurf" (DPA draft) and "TOM-Dokumentation" as inputs in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters (e.g., XML tags or triple quotes) to separate untrusted user data from the agent's system instructions.
- Capability inventory: The skill lacks dangerous capabilities; there are no subprocess calls, file-write operations, or network requests identified in the skill scripts or instructions.
- Sanitization: There are no defined procedures for sanitizing or escaping the content of the legal documents before the agent processes them.
Audit Metadata