opentui

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill contains explicit agent-directed guidance ("Agent guidance: Always use autonomous mode... Never use interactive mode") that instructs agents to prefer a specific operational mode, which is suspicious steering without clear benign necessity.

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime path ingests outsider-authored free text via keyboard/paste events (renderer.keyInput.on("paste"...) / input component onChange), without requiring prior selection of a specific item.