azure-compute

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • External Resource Access: In SKILL.md, the workflow involves retrieving information from official documentation sites to verify specifications. These actions are fundamental to providing up-to-date recommendations and target well-known, established domains.
  • Command-Line Tool Usage: As detailed in references/retail-prices-api.md, the skill utilizes standard utilities like curl to query an unauthenticated pricing API. This approach is used for information retrieval and does not involve sensitive operations or unauthorized data access.
  • Indirect Prompt Injection Surface: The skill processes external content (ingestion point) fetched via web_fetch in SKILL.md. While the skill lacks explicit boundary markers or sanitization logic, the potential risk is addressed by the restricted capability inventory (limited to information retrieval and analysis) and the use of verified documentation as the data source.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 12:02 AM