sprint-planner
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs its intended function of sprint planning by interacting with authorized external services (Jira, Linear, Azure DevOps, Confluence, Notion) via specific MCP adapters. All data processing is confined to the project's documentation and configured tracker environments.
- [COMMAND_EXECUTION]: The skill uses tools to read backlogs, create sprints, and publish documentation. A critical security control is present in Step 5, which mandates a user approval gate before any state-changing operations are performed on trackers or documentation backends.
- [DATA_EXFILTRATION]: The skill reads ticket data and specifications to build dependency graphs and capacity plans. This data is used solely to generate the sprint kickoff document and update tracker states. There is no evidence of data being transmitted to unauthorized third-party domains.
- [PROMPT_INJECTION]: The skill ingests untrusted data from ticket descriptions and requirement labels to infer dependencies. While this represents a surface for indirect prompt injection, the impact is limited to the local sprint plan and is subject to human review during the plan approval phase.
Audit Metadata