jira-automation

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

• Third-party content exposure detected (high risk: 0.85). The required runtime path uses Composio’s Jira tools (e.g., JIRA_SEARCH_FOR_ISSUES_USING_JQL_POST, JIRA_GET_ISSUE, JIRA_LIST_ISSUE_COMMENTS) which fetch outsider-authored Jira issue/comment text from the user’s Jira instance and feed it back into the agent context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires contacting the external MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS) to fetch tool schemas that directly determine available tools/instructions and are required for operation, so this external content can control agent behavior.