azure-durable-task
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is configured to fetch technical documentation from Microsoft's official domain (learn.microsoft.com), which is a trusted source for development guidelines.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external URLs, which represents a potential injection surface. 1. Ingestion points: Markdown content retrieved from learn.microsoft.com via documentation fetch tools. 2. Boundary markers: None defined within the instruction set for separating fetched content from agent instructions. 3. Capability inventory: The skill utilizes network-enabled tools to retrieve and display documentation. 4. Sanitization: The skill relies on the agent's standard handling of external Markdown content.
Audit Metadata