tarot-reading-expert

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow is to follow the “Research Checklist” which involves targeted web searches and recording/using newly fetched sources; this implies the agent may ingest outsider-authored free text from public web pages at runtime via the web research step.

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

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