backlog-manager

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

• Third-party content exposure detected (high risk: 0.90). The skill reads and interprets user-generated content from third-party issue systems—e.g., resources/github-backend.yml uses "gh issue list/ view --json" and resources/linear-backend.yml uses MCP calls (mcp__linear__get_issue / list) that return issue bodies/comments—so the agent consumes untrusted public content that could carry indirect prompt injections.