nis2-risikomanagement
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data regarding a company's infrastructure and compliance status. * Ingestion points: Inputs like 'Einordnung der Einrichtung', 'Inventar kritischer Systeme', and 'Notfallkonzepte' are provided by the user in SKILL.md. * Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings for the data being analyzed. * Capability inventory: The skill involves logic for gap analysis and roadmap generation across the Sub-Agent-Architektur defined in SKILL.md. * Sanitization: No sanitization or validation of the provided organizational details is specified before interpolation into the analysis prompt.
- [SAFE]: The skill references official legal documentation from well-known services, such as gesetze-im-internet.de and eur-lex.europa.eu, to provide context for the NIS2 risk assessment.
Audit Metadata