browser
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface
- Ingestion points: The skill reads arbitrary external web content in
index.jsviapage.goto(url)andpage.evaluate(). - Boundary markers: Absent. There are no delimiters or instructions to treat the fetched web content as untrusted data in the prompt context.
- Capability inventory: The skill uses
puppeteerto navigate and execute JavaScript on remote pages. - Sanitization: Absent. The script extracts raw
innerTextand returns it directly to the agent without filtering or sanitization. - [COMMAND_EXECUTION]: Reduced Browser Isolation
- The script in
index.jslaunches Puppeteer with the--no-sandboxand--disable-setuid-sandboxarguments. These flags disable Chromium's primary security isolation layer, which could allow a malicious website to exploit browser vulnerabilities to escape the process and execute code on the host system.
Audit Metadata