eventschemaset-cli

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill is designed to ingest and process Event Schema Set definitions (including event types and message schemas) retrieved from the Microsoft Fabric API. This data, which may be defined by other users or external systems, is decoded and parsed into the agent's active context.
  • Ingestion points: Event schema definitions are retrieved in references/consumption.md (Get Event Schema Set Definition) and processed for updates in references/authoring.md (Update Event Schema Set Definition).
  • Boundary markers: The instructions do not currently implement specific delimiters or 'ignore' instructions to isolate the external schema content from the agent's core operational logic.
  • Capability inventory: The skill has access to network and state-changing capabilities via the az rest tool, as well as data transformation capabilities using jq and base64 utilities.
  • Sanitization: The skill relies on structural parsing via jq and base64 encoding/decoding, but it does not perform semantic sanitization of the text fields within the schema (such as descriptions) which are presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 01:44 PM
Security Audit — agent-trust-hub — eventschemaset-cli