bitbucket-automation

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflows (e.g., "Manage Pull Requests" and "Review Pull Requests with Comments") explicitly instruct the agent to call Bitbucket endpoints such as BITBUCKET_GET_PULL_REQUEST_DIFF, BITBUCKET_GET_PULL_REQUEST, and BITBUCKET_LIST_ISSUES to fetch PR diffs, issue text, and comments — user-generated, third-party content the agent must read and that can directly influence actions like commenting, merging, or deleting.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires connecting to an external MCP server at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS) to fetch current tool schemas that directly influence agent behavior and are a required dependency, so this URL can control prompts/instructions.