design

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md Step Three requires auto-running "npx skills add pbakaus/impeccable" to fetch and install an external public package (pbakaus/impeccable) from the open web, which would introduce untrusted third‑party code/content that the agent will load and then use to drive subsequent skill calls and decisions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill auto-runs "npx skills add pbakaus/impeccable" at runtime, which fetches and executes remote code from the pbakaus/impeccable package repository (pbakaus/impeccable), so this external dependency can directly control agent behavior.