pp-superhuman

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

• Third-party content exposure detected (medium risk: 0.30). The Superhuman — Printing Press CLI runtime ingests outsider-authored email content via commands like messages list/query/get and watch, returning message text that an LLM agent may then use in --agent mode.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisite step runs "go install github.com/mvanhorn/printing-press-library/library/productivity/superhuman/cmd/superhuman-pp-cli@latest", which fetches and compiles remote code at runtime and is required for the skill to operate.