azure-deployment-environments

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates fetching technical documentation from official Microsoft domains (learn.microsoft.com). These references target well-known and trusted sources, which is standard and safe behavior for a documentation-focused skill.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its documentation-fetching functionality.\n
  • Ingestion points: Documentation content is retrieved through mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage as described in SKILL.md.\n
  • Boundary markers: Absent; the instructions do not provide explicit delimiters to separate external documentation content from the agent's primary instructions.\n
  • Capability inventory: The skill is limited to information retrieval and documentation assistance; it does not include capabilities for file system modification, arbitrary command execution, or unauthorized network exfiltration.\n
  • Sanitization: None; the skill processes documentation content as provided by the source, relying on the inherent trust of official Microsoft documentation repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 12:08 PM