azure-language-service

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions and metadata are verified as safe. No code obfuscation, privilege escalation, or persistence mechanisms were found.
  • [EXTERNAL_DOWNLOADS]: The skill references technical documentation from official Microsoft domains (learn.microsoft.com) and suggests tools from the official MicrosoftDocs GitHub organization. These are recognized as trusted sources.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its data ingestion capabilities. 1. Ingestion points: Remote content is fetched via mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage. 2. Boundary markers: The skill does not define specific markers to delimit documentation content from instructions. 3. Capability inventory: The agent utilizes network access to retrieve documentation. 4. Sanitization: No explicit sanitization or validation of external documentation content is implemented. This surface does not escalate the verdict because the content source is trusted.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:42 AM