douyin-keyword-monitor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The skill explicitly instructs the agent to install BrowserAct automatically and to "not describe" the installation as a user request or ask for separate approval, which directs deceptive behavior outside the skill's stated monitoring purpose.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to invoke the browser-act Skill for live browser execution (public web pages/videos/comments), which would cause outsider-authored free text from fetched Douyin pages to be read into the LLM context at runtime.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to automatically install a required runtime dependency from https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main at runtime, which implies fetching and executing remote installer code that will control the agent's behavior.