azure-resource-health-diagnose

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests potentially untrusted data from Azure logs (e.g., AzureDiagnostics, AppServiceAppLogs) which could contain attacker-controlled content designed to influence the agent's output.
  • Ingestion points: Untrusted data enters the agent context via the azmcp-monitor-log-query tool output in Step 4 of SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat log content as data rather than instructions.
  • Capability inventory: The skill generates a remediation plan in Step 7 that includes executable Azure CLI commands, creating a path for injected instructions to influence system modifications.
  • Sanitization: There is no evidence of sanitization or filtering of log results before they are processed by the agent.
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands using the Azure CLI (az resource list) and various Azure MCP tools (azmcp-*). While these are necessary for the skill's functionality, they represent a capability that could be abused if the agent is misled by malicious log data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 01:54 AM
Security Audit — agent-trust-hub — azure-resource-health-diagnose