azure-arc
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a curated index for Azure Arc documentation, linking exclusively to official Microsoft domains. No malicious patterns, obfuscation, or sensitive data exposure were detected.
- [EXTERNAL_DOWNLOADS]: Fetches documentation content from well-known Microsoft services (learn.microsoft.com). This behavior is the primary intended purpose of the skill and is handled via specialized tools like mcp_microsoftdocs:microsoft_docs_fetch.
- [COMMAND_EXECUTION]: The skill references various CLI tools and scripts (such as azcmagent, az arcdata, and cleanup scripts) within its documentation links, but it does not contain any code that executes these commands on the user's system.
- [DATA_EXFILTRATION]: No evidence of unauthorized data access or exfiltration. Network operations are limited to documentation retrieval from authoritative sources.
- [PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety constraints were found in the skill instructions.
Audit Metadata