ably-chat

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent to fetch runtime documentation (for example https://ably.com/llms.txt) and then "fetch target pages as needed" to inform code generation, meaning external content is fetched at runtime and can directly control prompts/instructions.