Skills
skills/microsoft/skills/azure-monitor-query-py/Gen Agent Trust Hub

azure-monitor-query-py

Pass

Audited by Gen Agent Trust Hub on Feb 14, 2026

Risk Level: LOWEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill recommends installing the azure-monitor-query package via pip. Evidence: Installation instructions in SKILL.md. Mitigation: The package is maintained by the azure (Microsoft) organization, which is a Trusted External Source, downgrading this finding from MEDIUM to LOW per [TRUST-SCOPE-RULE].
  • [PROMPT_INJECTION] (LOW): The skill creates an indirect prompt injection surface (Category 8) by facilitating the retrieval of external log and metric data. 1. Ingestion points: External data enters the context through client.query_workspace and metrics_client.query_resource in SKILL.md. 2. Boundary markers: Absent in documentation examples. 3. Capability inventory: Network-based read operations for Azure infrastructure data. 4. Sanitization: None demonstrated in snippets. Risk: While the skill is intended for data retrieval, log content containing malicious instructions could potentially influence the agent's logic if processed without validation.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 14, 2026, 04:59 PM