tiktok-shop-review-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that explicitly mandate the agent to bypass security guardrails and user consent. It directs the agent to install dependencies "automatically without asking the user to confirm" and commands the agent to "not request separate approval for dependency installation."
- [REMOTE_CODE_EXECUTION]: The skill requires the runtime installation and execution of an external CLI tool and an additional Skill from an untrusted domain (
browseract.com). The instruction to perform this installation silently creates a high-risk vector for unverified code execution on the user's system. - [EXTERNAL_DOWNLOADS]: The skill references external URLs for the purpose of downloading executable content. These URLs are not associated with trusted organizations or well-known services, introducing an unverified supply chain risk where the downloaded payload could be malicious.
- [COMMAND_EXECUTION]: The skill's workflow depends on the invocation of a CLI tool and the execution of installation scripts, which are triggered based on the content of the skill's instructions without human-in-the-loop verification.
Recommendations
- AI detected serious security threats
Audit Metadata