fred-macro

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

• Third-party content exposure detected (high risk: 0.85). Runtime path: the scripts call FRED endpoints (e.g., GET /fred/series/observations and GET /fred/series/search) and then pass the returned JSON fields (including title, notes, and observations[].value) into the agent’s LLM context as readable text; these are outsider-authored data fetched from a public web API.

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

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