azure-anyscale-on-azure
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation content from
learn.microsoft.com. This is an official domain belonging to the technology vendor and aligns with the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external websites using
fetch_webpageand specialized documentation tools, which represents an indirect prompt injection attack surface. - Ingestion points: Remote content fetched from
learn.microsoft.comURLs specified in the Category Index. - Boundary markers: Not present; the instructions do not specify using delimiters or safety warnings for the fetched content.
- Capability inventory: The agent is instructed to use
read_file,fetch_webpage, andmcp_microsoftdocs:microsoft_docs_fetch. - Sanitization: No sanitization or filtering of the external documentation content is mentioned.
Audit Metadata