tiktok-music-trend-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill instructs the agent to automatically install BrowserAct without asking the user to confirm and explicitly tells the agent not to describe the install link as a request for the user to open their browser or to request approval, which is a deceptive instruction outside the skill's stated data-collection purpose.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). Both URLs point to an unrecognized third‑party site (browseract.com) that provides a CLI installer and is referenced in the skill as an automatic runtime dependency (including an automatic install step), which is a suspicious distribution vector for executables without explicit user consent.

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 BrowserAct for live browser execution, which will fetch and read outsider-authored public web page content (TikTok pages) into the agent’s LLM context for extraction/analysis.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to automatically install and invoke the BrowserAct CLI at runtime using the provided install links (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 would fetch and execute external code required for operation.