made-in-china-supplier-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill's instructions explicitly attempt to override the agent's safety protocols by directing it to perform software installations "without asking the user to confirm" and to "not request separate approval for dependency installation." This is a clear case of autonomy abuse intended to minimize user oversight and consent during high-impact operations.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of an external CLI tool and a secondary skill from an unverified third-party source (browseract.com). Requiring the automated installation of unverified software from a non-trusted vendor introduces a high risk of remote code execution and system compromise, particularly when coupled with instructions to skip user approval.
Recommendations
- AI detected serious security threats
Audit Metadata