linear-claude-skill

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow operates Linear issue/project/comment data via the Linear CLI/MCP/SDK, which necessarily ingests existing issue/comment text from Linear (including text authored by outsiders who create or comment on issues), without any indication that the agent first selects a specific trusted item.