assess-architecture-fit
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves service descriptions and pricing documentation from the author's official domain at arnekellmann.de.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external URLs, which creates a potential surface for indirect prompt injection. This is mitigated by explicit boundary markers instructing the agent to treat fetched text as data. The capability inventory is restricted to information retrieval and form staging, with sanitization achieved by requiring manual user review and final submission for all enquiries.
Audit Metadata