tiktok-comment-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill contains explicit, deceptive instructions to install a runtime dependency automatically and to conceal that installation from the user (not asking for confirmation and not describing it as a user-facing request), which is outside the stated scraping purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This Skill explicitly instructs automatic installation of an external CLI dependency and tells the agent not to request or disclose user approval for that installation, enabling unauthorized installation and potential supply-chain abuse.

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 pages at runtime and then work with “Comment text” and related fields, which implies outsider-authored free text (public/authorized TikTok comments/captions) is ingested into the LLM context via the BrowserAct page-extraction workflow.

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 the BrowserAct CLI at runtime using the provided install URLs (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 implies fetching and running remote installer code as a required runtime dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The Skill explicitly directs the agent to install the BrowserAct dependency automatically without asking the user for confirmation, which instructs the agent to modify the host system by installing software and thus risks changing machine state without approval.