azure-pricing

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches real-time pricing data and billing rates from official Microsoft domains, including prices.azure.com and learn.microsoft.com.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from external documentation to perform cost calculations and uses user input to construct OData filters for API requests, which represents an indirect prompt injection surface.
  • Ingestion points: The skill fetches billing rates and licensing rules from learn.microsoft.com (specified in SKILL.md) and uses this data to calculate estimated costs.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content embedded in the fetched documentation.
  • Capability inventory: The skill utilizes web fetch tools and performs mathematical calculations based on the ingested content.
  • Sanitization: The skill does not define specific validation or sanitization routines for the content retrieved from external URLs or for the user-supplied values used to build API filter strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:58 AM
Security Audit — agent-trust-hub — azure-pricing