debugging-devtools-extensions

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses platform-specific commands to automate local development tasks.
  • It uses flutter run to launch the DevTools application and sample apps locally.
  • It utilizes system-level browser opening utilities (open on macOS, xdg-open on Linux, and start on Windows) to navigate to the local DevTools URL.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a process where a user-provided VM Service URI is interpolated into a shell command to open a browser.
  • Ingestion points: The agent is instructed to ask the user for a VM Service URI to be used in the URL parameter (Step 3).
  • Boundary markers: The instructions do not include specific delimiters or warnings to ignore instructions within the user-provided URI.
  • Capability inventory: The skill uses OS shell commands to open URLs containing the user input.
  • Sanitization: No specific sanitization or escaping mechanisms are described for the user-provided URI before it is executed in the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 08:43 AM
Security Audit — agent-trust-hub — debugging-devtools-extensions