pp-sentry

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

• Third-party content exposure detected (medium risk: 0.30). The skill provides a CLI wrapper for Sentry to read issues, events, and projects, which can contain user-submitted error messages and stack traces.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to install an unverified third-party Go package and npm package from a personal GitHub repository and npm scope (@mvanhorn/...) during setup/runtime, which constitutes a weak/unknown provenance operational dependency.