azure-operator-service-manager

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation from official Microsoft domains (learn.microsoft.com) and references the MicrosoftDocs GitHub organization for utility installation. These are trusted vendor sources.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest untrusted data from external web pages which could contain instructions meant to influence the agent's behavior.
  • Ingestion points: External documentation is retrieved via mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage tools.
  • Boundary markers: None. The skill does not define specific delimiters or "ignore instructions" wrappers for the fetched content.
  • Capability inventory: The skill has no capabilities for file writing, subprocess execution, or network data exfiltration.
  • Sanitization: There is no evidence of content sanitization or validation of the fetched markdown.
  • [NO_CODE]: The skill consists exclusively of markdown documentation and guidance. No scripts, binaries, or active code components are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:41 AM