analyzing-azure-activity-logs-for-threats
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data from Azure Monitor and Log Analytics workspaces, which represents an indirect prompt injection surface. If an attacker can generate log events (e.g., via failed sign-ins or resource modifications), they could attempt to embed instructions to influence the agent's interpretation of findings.
- Ingestion points: Data is ingested via
LogsQueryClient.query_workspaceinscripts/agent.pyand visualized through KQL queries. - Boundary markers: The skill does not use specific delimiters or instructions to ignore embedded commands within the processed log data.
- Capability inventory: The script
scripts/agent.pycan read log data and write findings to a local file (azure_threat_report.json). It does not have access to arbitrary shell execution or network exfiltration tools beyond the Azure APIs. - Sanitization: There is no evidence of sanitization or escaping of log content before it is processed or written to the output report.
Audit Metadata