stably-cli

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to run stably verify with a user-supplied --url and to run stably fix which analyzes traces, screenshots and DOM state, meaning the agent will fetch and interpret arbitrary web pages/third-party content (e.g., the target URL and DOM) as part of its workflow.