faster-chrome-devtools-skill
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill interacts with external web content, creating a surface for indirect prompt injection where malicious data on a webpage could attempt to influence the agent's behavior.
- Ingestion points:
scripts/cdp.mjs(commands: snapshot, evaluate, html, console, failures) - Boundary markers: Absent
- Capability inventory:
scripts/cdp.mjs(commands: click, fill, navigate, evaluate) - Sanitization: Absent
- [COMMAND_EXECUTION]: The skill provides a tool (
scripts/cdp.mjs) for executing browser commands and evaluating JavaScript within the browser context. This is the primary intended functionality of the skill. - [DATA_EXFILTRATION]: The skill facilitates the extraction of page content, console logs, and screenshots from the browser. This data is intended for use by the agent to perform its tasks.
Audit Metadata