company-signals

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

• Third-party content exposure detected (low risk: 0.10). The workflow queries public company signals and records (rankings, job postings, SEC Form D filings, subdomains, trademarks) via an MCP shell, which can contain outsider-authored text and keyword data.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs connection to the remote MCP server at https://mcp.hedwigai.com/ and installation from an external plugin marketplace, representing an unverifiable third-party operational dependency.