telnyx-ai-assistants-java

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly supports a dynamicVariablesWebhookUrl (see the optional parameters in references/api-details.md and mentions in SKILL.md), meaning the assistant will call arbitrary external webhook URLs to fetch dynamic variables that can change assistant instructions/behavior, exposing the agent to untrusted third-party content that could influence actions.