azure-resource-health-diagnose
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted telemetry and log data from Azure resources, creating an attack surface for indirect prompt injection.
- Ingestion points: Log data is retrieved using the
azmcp-monitor-log-querytool as described inSKILL.md(Step 4). - Boundary markers: The instructions do not include specific delimiters or warnings to the agent to disregard potential instructions embedded within the retrieved logs.
- Capability inventory: The agent is instructed to generate and potentially execute Azure CLI commands for remediation (Step 6), which could be manipulated by an attacker who can inject text into the Azure logs being analyzed.
- Sanitization: There is no mention of sanitization or validation of the log content before it is parsed by the LLM for diagnosis and planning.
Audit Metadata