azure-carbon-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is designed to retrieve documentation from official Microsoft Learn domains (learn.microsoft.com) using specific MCP tools or general web fetching. These are neutral operations intended for providing documentation context.- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, which represents a potential attack surface. However, the risk is negligible as it targets only official vendor documentation sites.
- Ingestion points: Documentation content fetched from learn.microsoft.com via mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage.
- Boundary markers: No specific delimiters or safety instructions are defined to separate fetched content from skill instructions.
- Capability inventory: The skill allows for file reading and web fetching but does not provide capabilities for file system modification, command execution, or non-whitelisted network exfiltration.
- Sanitization: No explicit sanitization or validation of the fetched documentation content is implemented within the skill definition.
Audit Metadata