hr-personal-kanzlei-intake

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external documents ("Material") provided by users, such as contracts, administrative records, and certificates.
  • Ingestion points: The "Direktstart" and "Arbeitsweg" sections instruct the agent to read and analyze provided documents to create work products.
  • Boundary markers: The instructions do not specify the use of delimiters or clear separation between system instructions and the untrusted content being processed.
  • Capability inventory: The skill generates markdown outputs (e.g., personalstammblatt.md) and performs legal assessments based on input data.
  • Sanitization: No sanitization, validation, or escaping of the external document content is mentioned before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 03:55 PM