fomc-monitor

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

• Third-party content exposure detected (high risk: 0.85). The skill’s required runtime workflow uses WebFetch to retrieve and “read it fully” the FOMC statement and prior statement from federalreserve.gov (public web content authored by the Fed), which is outsider-authored free text relative to the operating user.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly performs runtime WebFetches of Federal Reserve pages (e.g., https://www.federalreserve.gov/newsevents/pressreleases/monetary20260429a.htm and https://www.federalreserve.gov/monetarypolicy/fomccalendars.htm) and requires fetching the actual FOMC statement pages at runtime to drive and populate the agent's prompts/outputs, so the external content directly controls the agent's behavior.