eu-ai-act-classification
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security issues detected. The skill consists entirely of instructional markdown and reference documentation for regulatory compliance. It does not ship with any executable scripts or configuration files that could be used for malicious purposes.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided descriptions of AI systems to perform its classification task.
- Ingestion points: User input provided via the 'Quick Question Set' in
SKILL.mdor general descriptive prompts. - Boundary markers: Not explicitly defined; the skill relies on the LLM's following of the structured decision tree.
- Capability inventory: The skill only performs text generation (Memos, Risk Registers, Summaries). No tools, subprocesses, or network operations are invoked.
- Sanitization: No specific sanitization or filtering is performed on input data. However, given the lack of dangerous capabilities, the risk remains negligible.
Audit Metadata