douyin-topic-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill contains explicit instructions to install dependencies automatically and to avoid asking or clearly informing the user (e.g., "without asking the user to confirm" and "Do not describe it as a request..."), which are deceptive operational directives outside the stated scraping/data-collection purpose.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to invoke the BrowserAct CLI to access real Douyin web pages at runtime (public web content fetched/scraped), which can include outsider-authored free text (e.g., captions/notes/metadata) that may be ingested into the LLM context.

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 fetch/install and invoke BrowserAct at runtime using the Install BrowserAct links (https://www.browseract.com/?co-from=social-media and https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which are required runtime dependencies that will retrieve and install remote code for execution.