jira

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

• Third-party content exposure detected (high risk: 0.75). The required workflow uses ClawLink to “browser login”/authorize Jira and then the agent runs Jira actions that fetch issue/user/group data (outsider-authored Jira content) which is read into the agent’s context via the CLI’s returned text/JSON.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to run "npx @useclawlink/cli" (and related CLI commands) which fetches and executes remote code from the npm package/ClawLink service (https://www.npmjs.com/package/@useclawlink/cli and https://claw-link.dev) at runtime, and this external code is a required dependency that can directly control the agent's actions.