postlauf
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill processes incoming messages from various channels including beA (ZIP exports), email, faxes, and messengers as described in the 'Triage zu Beginn' and 'Ablauf' sections.
- Boundary markers: There are no specific delimiters or instructions provided to the agent to ignore potentially malicious content embedded within the processed legal documents or messages.
- Capability inventory: The skill performs file management, tool invocation (
kanzlei-allgemein-bea-journal), and archive extraction ('entpacken'). - Sanitization: No explicit sanitization or validation steps for the content of the ingested messages are mentioned.
- [SAFE]: The skill includes a feature to set a daily reminder at 11 AM. While this involves scheduling, it is performed transparently by asking the user for permission and is directly related to the skill's primary function of managing the 11 AM mail run.
Audit Metadata