api-license-sdk
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted external data such as contracts and legal documents.
- Ingestion points: The skill instructions in
SKILL.mdspecify processing "Verwaltungsakte, Vertragsurkunden, Schriftsätze, Bescheide" (administrative acts, contracts, pleadings, and notices) provided by the user. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential prompts embedded within these external documents.
- Capability inventory: The agent is instructed to perform web-based research on public legal portals and generate complex legal work products (memos, license drafts, and redlines).
- Sanitization: There are no requirements for sanitizing or filtering input documents before the agent processes them.
- [EXTERNAL_DOWNLOADS]: The skill workflow involves accessing external legal information services.
- Finding: The instructions guide the agent to verify legal statutes via well-known and public German legal portals, including
gesetze-im-internet.de,dejure.org, andopenJurto ensure accuracy.
Audit Metadata