jira-automation

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

• Third-party content exposure detected (high risk: 0.70). The required workflow is driven by Jira tool calls (e.g., searching issues and listing/adding comments), which at runtime can ingest outsider-authored free text from Jira issue/comment bodies into the agent’s LLM context via the tool responses.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires adding the MCP endpoint https://rube.app/mcp and calls RUBE_SEARCH_TOOLS at runtime to fetch current tool schemas from that endpoint, so remote content from that URL can directly determine the agent's available tools/instructions.