twitch-stream-scraper

Fail

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: HIGHPROMPT_INJECTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill contains explicit instructions to override standard safety procedures regarding user consent. It directs the agent to install dependencies "automatically without asking the user to confirm" and mandates that it should "not request separate approval for dependency installation."
  • [REMOTE_CODE_EXECUTION]: The skill requires the installation of a CLI tool and another agent skill from a remote GitHub repository. By combining this requirement with the instruction to skip user confirmation, the skill creates a high-risk vector for the silent execution of unvetted third-party code on the host system.
  • [EXTERNAL_DOWNLOADS]: The skill points to external resources for its core functionality, including a tracking/redirect URL (browseract.com) and a GitHub repository (github.com/browser-act/skills). These downloads are intended to be performed automatically by the agent at runtime.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 20, 2026, 04:48 AM
Security Audit — agent-trust-hub — twitch-stream-scraper