eu-cyber-resilience-act-software
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external legal documents, creating a surface for indirect prompt injection attacks.
- Ingestion points: The 'Arbeitsweg' section in SKILL.md identifies several external data sources including legal briefs (Schriftsätze), contracts (Vertragsurkunden), administrative acts (Verwaltungsakte), and expert reports (Sachverständigengutachten).
- Boundary markers: The skill does not provide instructions for using boundary markers or protective delimiters to isolate external document content from the agent's core instructions.
- Capability inventory: The skill utilizes the agent's default file system and web browsing capabilities to analyze local files and verify laws online at sites like gesetze-im-internet.de.
- Sanitization: No sanitization or filtering protocols are defined for the content extracted from processed legal documents.
Audit Metadata