instantly-campaigns

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

• Potentially malicious external URL detected (high risk: 0.90). Yes — the skill calls the Anthropic API (model "claude-opus-4-5-20251101" via the anthropic client, e.g. https://api.anthropic.com) at runtime and directly uses the model's generated JSON to control campaign content, so remote content from that URL directly controls the agent's output and is a required dependency.