runhuman-testing

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs agents at runtime to fetch and follow external instruction content—e.g., "Fetch the comprehensive agent guide at https://runhuman.com/for_agents_github_actions.md" (and to check https://github.com/volter-ai/runhuman-action/releases for the latest action version), meaning external content is retrieved during runtime and directly controls agent instructions.