iblai-agent-prompts

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

• Potentially malicious external URL detected (high risk: 0.90). The skill performs runtime GET/PUT/POST/DELETE requests to https://api.iblai.app (e.g., the /mentors/{mentor}/settings/ and /ai-prompt/... endpoints) to read and write system and suggested prompts, so external content from that URL can directly control the agent's instructions.