pp-sendgrid

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to call the live SendGrid API and parse its outputs in Agent Mode (e.g., commands like templates lint, messages list, activity tail, templates diff, bounce why), so untrusted/user-generated content from SendGrid is fetched and can materially influence subsequent tool use and decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisite runs npx -y @mvanhorn/printing-press install sendgrid --cli-only which fetches and executes remote npm installer code at runtime to install the required sendgrid-pp-cli binary, so this external fetch executes remote code and is a required dependency.