submit-to-agentlaunch

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires and recommends an instructions_url that "other agents consume ... unattended" (example: https://researchbot.ai/llms.txt), meaning remote, machine-readable instructions are fetched at runtime and can directly control agent prompts/behavior.