coderabbit

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly integrates with Git platforms and PR commands (see SKILL.md and references/pr-commands.md and references/platforms.md), including reading PR comments, triggers like "@coderabbitai run ", and traversing linked repositories—all of which are user-generated / third‑party content the agent is expected to read and act on as part of the workflow, creating exposure to indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires the CodeRabbit CLI and repeatedly instructs installing it by fetching and executing a remote installer (curl -fsSL https://cli.coderabbit.ai/install.sh | sh), which is a runtime external dependency that runs remote code.