ad-creative-generation

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

• Third-party content exposure detected (low risk: 0.10). The workflow extracts brand identity and website screenshots using firecrawl_branding_extract from user-supplied website URLs, exposing the agent to external web content.

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

• Potentially malicious external URL detected (high risk: 0.70). The referenced https://app.hyperfx.ai/mcp URL points to an external third-party MCP platform and service required for tool execution and brand extraction, constituting an unverifiable operational dependency with unknown publisher provenance.