boards-team-active-work
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- Interaction with Well-Known Services: The skill interacts with
dev.azure.com, which is an established service for project management. The tools used (core_list_projects,wit_backlog, etc.) are standard for Azure DevOps integration, and the generated links follow official URL patterns for work item editing. - Data Ingestion Considerations: As this skill processes work items (including user-generated titles and relation data), it possesses a surface for potential indirect prompt injection. However, since the skill is restricted to displaying this data and does not possess capabilities like file system writing or arbitrary command execution, this represents a standard operational risk handled by the platform's underlying safety layers.
- Ingestion points: Work item titles, states, and relation details are fetched from the Azure DevOps API via the
wit_work_itemandwit_backlogtools. - Boundary markers: The skill instructions do not explicitly define delimiters for external data, but the output is strictly structured into markdown tables and lists.
- Capability inventory: The skill is limited to read operations and formatted display; it does not have access to shell commands, network requests to third-party domains, or persistent storage.
- Sanitization: The skill relies on the agent's default handling of external text during formatting.
Audit Metadata