truefoundry-mcp-servers

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests remote third-party content at runtime—notably remote OpenAPI specs for mcp-server/openapi (SKILL.md "Remote OpenAPI specs are fetched at runtime...") and agent_card_url/hosted-a2a-agent sources in references/manifest-schema—that can be converted into MCP tools or influence agent behavior, meaning untrusted external URLs can materially change tool capabilities and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches remote OpenAPI specs at runtime (e.g., https://internal-api.example.com/openapi.json, https://api.weather.example.com/openapi.json) which are auto-converted into MCP tools that directly control agent capabilities, and it also fetches hosted A2A agent cards at runtime (e.g., https://research-agent.example.com/.well-known/agent.json), so these external URLs are runtime dependencies that can change agent prompts/behavior.