sentry-cli

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow uses the sentry CLI to fetch and display Sentry issue/trace/log/event content (e.g., via sentry issue view, sentry trace view, sentry log list, sentry event list), and that fetched text can include outsider-authored free-form fields like issue titles/messages, log messages, and stack traces that the agent then reads into its LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's installation instructions recommend running a runtime fetch-and-execute command (curl https://cli.sentry.dev/install -fsS | bash), which downloads and immediately executes remote code from https://cli.sentry.dev/install and is presented as a required/primary way to install the required CLI dependency.