hedwigai

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

• Third-party content exposure detected (medium risk: 0.30). The skill queries public records, filings, web traffic, and social feeds via the hedwigai MCP, which can ingest outsider-authored content from public web and social sources.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill integrates a remote Model Context Protocol server and plugin marketplace from third-party publisher un-seen, representing a common unofficial operational dependency.