atlassian-integration

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and parse user-generated content from external Atlassian instances (e.g., "Confluence Doc Generation from Jira Sprint" and the listed MCP tools like confluence_get_page and jira_get_issue) and then use that content to decide or perform actions (create/update pages, transition issues), so untrusted third-party content can influence tool use.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's MCP configuration invokes "npx -y @atlassian/mcp-atlassian" which at runtime fetches and executes remote code from the npm registry (https://registry.npmjs.org/@atlassian/mcp-atlassian) and is required to provide the MCP tools, so it is a runtime external dependency that executes remote code.