stophy-browser
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is configured to use
npxto download and execute the@stophy/clipackage from the NPM registry. This package is the official CLI tool provided by the skill's author.- [COMMAND_EXECUTION]: The skill executesstophyCLI commands via the Bash tool to perform browser tasks, such as navigating to URLs, clicking elements, and filling forms.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external websites to fulfill user-defined goals, creating a surface for indirect prompt injection where a website could contain malicious instructions designed to subvert the agent. - Ingestion points: Web content retrieved from URLs provided to the
stophy browsercommand. - Boundary markers: No specific delimiters or "ignore instructions" wrappers are defined in the command examples for the website content or goal strings.
- Capability inventory: The skill is limited to executing the
stophyCLI tool, which communicates with a remote browser service. It does not have direct access to sensitive local files or general network tools in the provided examples. - Sanitization: The instructions do not describe specific sanitization or filtering of the website content before it is processed by the agent.
Audit Metadata