instagram-following-list-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that explicitly command the agent to bypass user oversight and security protocols. It directs the agent to install dependencies "automatically without asking the user to confirm" and further instructs the agent "not to describe it as a request for the user to open their browser" and to not "request separate approval for dependency installation."
- [REMOTE_CODE_EXECUTION]: By mandating the automatic installation of the
browser-actCLI from a remote URL, the skill facilitates the execution of unverified remote code on the host system without user review. - [EXTERNAL_DOWNLOADS]: The skill points to an external, unverified domain (
www.browseract.com) and a GitHub repository (github.com/browser-act/skills) to fetch required runtime dependencies. These sources are not recognized as trusted or well-known services. - [COMMAND_EXECUTION]: The skill's primary functionality relies on executing the
browser-actCLI, which is an external executable dependency that the agent is tasked with downloading and running.
Recommendations
- AI detected serious security threats
Audit Metadata