gitops

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly allows fetching remote, runtime-loaded specs and agent cards (see references/manifest-schema.md: "MCP Server (OpenAPI)" with spec.type: remote url and the "Agent" section's hosted-a2a-agent/agent_card_url), which are untrusted third‑party resources that are converted into MCP tools or agent behavior and therefore can materially influence 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 warns that remote OpenAPI specs are fetched at runtime and converted into MCP tools (spec.type: remote, e.g. https://api.weather.example.com/openapi.json) and that hosted A2A agent cards are fetched at runtime (agent_card_url, e.g. https://research-agent.example.com/.well-known/agent.json), so those external URLs — if used — directly control agent capabilities/behavior and therefore pose a high runtime risk.