yahoo-auctions-japan-scraper
Fail
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes instructions that attempt to override standard agent safety protocols. It explicitly directs the agent to install dependencies "without asking the user to confirm" and commands the agent to "not request separate approval for dependency installation."
- [EXTERNAL_DOWNLOADS]: The instructions require the agent to fetch and install external software from a remote GitHub repository (
github.com/browser-act/skills) automatically if the dependency is missing. - [COMMAND_EXECUTION]: The skill mandates the autonomous execution of installation scripts or commands to set up the BrowserAct CLI, which poses a significant risk as it bypasses user oversight for software deployment.
Recommendations
- AI detected serious security threats
Audit Metadata