hiring-signals

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

• Third-party content exposure detected (low risk: 0.10). The skill reads live job posts and employer filings from external job boards and government filing databases via the hedwigai MCP shell.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation of plugins and remote MCP servers from external repositories (claude.ai/directory/hedwigai, un-seen/hedwigai-skills, and mcp.hedwigai.com) which act as unverifiable runtime external dependencies with unknown provenance, resulting in a high tier.