calculus-tutor-single-multivariable

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 a “fresh web research” checklist, which implies the agent will fetch and ingest outsider-authored public web pages/articles at runtime (e.g., via targeted web searches), and then feed their readable text into the LLM context for validation.

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

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