The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches documentation from learn.microsoft.com and provides instructions to install a tool from the MicrosoftDocs GitHub repository. These resources belong to a well-known service and a trusted organization.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection.
Ingestion points: External content is retrieved using mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage based on the numerous Microsoft Learn URLs provided in SKILL.md.
Boundary markers: Absent. The skill does not include specific instructions or delimiters to isolate fetched content or prevent the agent from following instructions embedded within the documentation.
Capability inventory: The skill uses read_file, fetch_webpage, and mcp_microsoftdocs:microsoft_docs_fetch to interact with and process data.
Sanitization: Absent. There is no evidence of validation or filtering of the fetched content before it is processed by the agent.

azure-translator