bitbucket

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

• Third-party content exposure detected (high risk: 0.80). The skill uses Membrane to connect to Bitbucket and run actions (e.g., list-pull-request-comments, list-issues, get-pull-request, list-commits) that fetch user-generated content from repositories, PRs, and comments — content the agent is expected to read and that could materially influence subsequent actions.