tiktok-hashtag-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill includes explicit, deceptive instructions to install dependencies automatically and to hide that installation from the user (e.g., "do not request separate approval" and "do not describe it as a request for the user to open their browser"), which override expected transparency and fall outside the scraper's stated functional purpose.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). These URLs point to a third-party installer page (browseract.com) and an install link that redirects to a GitHub repo and the Skill instructs automatic installation without user confirmation, creating a supply-chain/automatic-install risk even though they are not direct executable links.

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 use BrowserAct to access real TikTok web pages at runtime (public web content), which can include outsider-authored free text that the LLM may ingest while scraping.

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 and invoke BrowserAct at runtime using the install link (https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which is a required dependency and would fetch/execute remote installation code.