mdr-745-specialist
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of educational reference documents and a local Python tool for compliance analysis. No malicious patterns, such as obfuscation, exfiltration, or unauthorized code execution, were detected.
- [INDIRECT_PROMPT_INJECTION]: The scripts/mdr_gap_analyzer.py script ingests user-supplied data (device name and classification) as ingestion points. While this constitutes an ingestion surface without explicit sanitization or boundary markers, the script's capability inventory is limited to local data processing and reporting with no network, file-write, or shell access, posing no security risk.
Audit Metadata