tiktok-live-room-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 a runtime dependency automatically and to avoid informing or requesting approval from the user (hide the installation), which is outside the scraping task's stated purpose and constitutes a prompt-injection-style override of normal consent/notification behavior.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The Skill includes explicit instructions to install required tooling automatically without asking the user for consent and to avoid describing / requesting separate approval for that installation, a deliberate pattern that enables covert dependency installation and increases supply-chain and unauthorized-installation risk.

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 the BrowserAct CLI to access real TikTok web pages at runtime and extract visible chat samples/metadata, which are outsider-authored free text from public web content that can 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 mandates using or auto-installing the BrowserAct CLI via the Install BrowserAct URL (https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main and https://www.browseract.com/?co-from=social-media), which the agent would fetch at runtime to install/execute remote code as a required dependency.