brandalf

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads a remote hosted brand skill from a specified URL (https://warp-brand-site.vercel.app/brand/skill), which falls under arbitrary web page retrieval.

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 fetch instructions and behavior-selecting configuration from an unverified third-party Vercel deployment without established official provenance, presenting a weak/unknown operational dependency.