homeoffice-und-arbeitszimmer
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted external data as part of its core functionality, creating a surface for indirect prompt injection.
- Ingestion points: The agent is explicitly instructed to collect and review external documents such as contracts (Werkvertrag/Dienstvertrag), tax declarations, and invoices (SKILL.md).
- Boundary markers: The instructions do not prescribe the use of delimiters or specific safety markers to differentiate between the document content and the agent's instructions.
- Capability inventory: The skill directs the agent to evaluate legal risks and perform a 'Live-Check' for tagesaktuelle Normänderungen (daily legal updates), which likely utilizes search or web-retrieval tools.
- Sanitization: There are no procedures defined within the skill for sanitizing or filtering the content of these processed documents to prevent the execution of embedded instructions.
Audit Metadata