swiftui-design-skill

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

• Third-party content exposure detected (high risk: 0.75). The “Brand Asset Integration Protocol” (Workflow 2) explicitly uses web_search and downloads/extracts brand guidelines/press kits at runtime, which can include outsider-authored free text that the agent would ingest into the LLM context to derive colors/fonts/tokens.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)