The Agent Skills Directory

[SAFE]: The skill provides documentation for Azure observability tools and commands. No malicious patterns, prompt injections, or unauthorized data access attempts were detected.
[INDIRECT_PROMPT_INJECTION]: The skill provides instructions for querying external logs (via Azure Log Analytics and Kusto). While this represents a potential surface for indirect prompt injection if external logs contain malicious instructions, the skill itself provides standard reference materials and uses well-known Azure CLI tools. Evidence:
Ingestion points: az monitor log-analytics query and azure__kusto MCP tools read external log data.
Boundary markers: None specified in the documentation examples.
Capability inventory: Shell command execution via Azure CLI and Kusto query execution.
Sanitization: None specified in the provided reference snippets.

azure-observability