linear-automation

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests outsider-authored free text via user-provided Linear fields like title, description, and especially body for LINEAR_CREATE_LINEAR_COMMENT/LINEAR_UPDATE_LINEAR_COMMENT, which the agent sends to Linear and therefore reads/handles at execution time.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires adding and connecting to the MCP endpoint "https://rube.app/mcp" and to call RUBE_SEARCH_TOOLS to fetch current tool schemas at runtime, meaning remote content from that URL will directly control available tool prompts/behavior.