atlassian-mcp

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses Atlassian MCP tool calls (e.g., jira_search, jira_get_issue, confluence_search, confluence_get_page) that ingest Jira/Confluence issue/page text authored by other users into the agent’s LLM context via the tool results (outsider-authored content from authenticated Atlassian tenants).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's MCP server configuration invokes external package runners that fetch and execute remote code at runtime (e.g., "npx @anthropic/mcp-atlassian", "npx @sooperset/mcp-atlassian" / "uvx mcp-atlassian"), which are required runtime dependencies and therefore present remote-code-execution risk.