gdd

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated content from third-party services (e.g., Jira via the Atlassian MCP "searchJiraIssuesUsingJql" in sub-skills/init and code-like-me, and Figma via MCP "get_design_context" in sub-skills/plan and implement) and then reads and uses that content to build plans and drive implementation decisions, so untrusted third-party content can materially influence agent actions.