lead-lists

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads public profile pages and web search results via the outreach program to find company and people information.

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 external MCP servers and plugin directories via https://claude.ai/directory/hedwigai, un-seen/hedwigai-skills, and https://mcp.hedwigai.com/, which lack established first-party enterprise provenance.