cloud-alignment

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE] (SAFE): No malicious instructions, obfuscation, or hardcoded credentials were found in the skill or reference files.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill fetches documentation from trusted Microsoft domains using specialized MCP tools; no arbitrary remote code execution or unauthorized downloads were detected.
  • [PROMPT_INJECTION] (LOW): Potential indirect prompt injection surface exists through documentation fetching. 1. Ingestion: mcp__microsoft-learn__microsoft_docs_fetch in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Read, Glob, Grep in SKILL.md. 4. Sanitization: Absent. Risk is categorized as low due to the absence of dangerous system capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:27 PM