ai-act-knowledge
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [SAFE]: No malicious patterns, command execution, or persistence mechanisms were detected. The skill's primary purpose is to provide grounded answers to regulatory questions using provided static reference files.
- [EXTERNAL_DOWNLOADS]: The skill contains numerous hyperlinks to official European Union domains (ec.europa.eu, enisa.europa.eu, eur-lex.europa.eu) and established institutional sources (humanrights.dk, eba.europa.eu). These are well-known, trusted services used for referencing official documentation.
- [NO_CODE]: No executable scripts (Python, Node.js, Shell), configuration files for package managers, or runtime dependencies are included in the skill. It consists strictly of instructions and markdown data.
- [PROMPT_INJECTION]: Instructions in SKILL.md focus on preventing hallucinations and maintaining a strict source hierarchy. No attempts to bypass safety filters or override core agent behavior were found.
Audit Metadata