805-regulations-eu-cyber-resilience-act
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, designed to help engineers and architects perform compliance reviews. It contains no executable scripts, hardcoded credentials, or persistence mechanisms.
- [EXTERNAL_DOWNLOADS]: The instructions explicitly forbid fetching external regulatory data at runtime, directing the agent to use bundled local markdown files instead. This prevents potential data exfiltration or ingestion of malicious external content.
- [PROMPT_INJECTION]: The skill contains no attempts to override system prompts or bypass safety guardrails. Its constraints are focused on ensuring the AI provides engineering context rather than legal advice.
- [DATA_EXFILTRATION]: No network-enabled tools or patterns were identified. The skill does not attempt to send data to external domains.
- [COMMAND_EXECUTION]: There are no shell commands, dynamic code execution patterns (eval/exec), or platform-specific dynamic context injections ($ARGUMENTS/backticks) in the provided files.
Audit Metadata