brida-reflex

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads online discovery files and external user inputs when performing discovery or support ticket triage.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references https://brida.ai/reflex/llms.txt, agent.md, and agent.json as live operational discovery sources, but the domain brida.ai represents an unverified third-party/personal context without established first-party enterprise authority for this hypothetical project, placing it in the weak/unknown provenance tier.